Si Li


2024

pdf bib
Visual Enhanced Entity-Level Interaction Network for Multimodal Summarization
Haolong Yan | Binghao Tang | Boda Lin | Gang Zhao | Si Li
Findings of the Association for Computational Linguistics: NAACL 2024

MultiModal Summarization (MMS) aims to generate a concise summary based on multimodal data like texts and images and has wide application in multimodal fields.Previous works mainly focus on the coarse-level textual and visual features in which the overall features of the image interact with the whole sentence.However, the entities of the input text and the objects of the image may be underutilized, limiting the performance of current MMS models.In this paper, we propose a novel Visual Enhanced Entity-Level Interaction Network (VE-ELIN) to address the problem of underutilization of multimodal inputs at a fine-grained level in two ways.We first design a cross-modal entity interaction module to better fuse the entity information in text and the object information in vision.Then, we design an object-guided visual enhancement module to fully extract the visual features and enhance the focus of the image on the object area.We evaluate VE-ELIN on two MMS datasets and propose new metrics to measure the factual consistency of entities in the output.Finally, experimental results demonstrate that VE-ELIN is effective and outperforms previous methods under both traditional metrics and ours.The source code is available at https://github.com/summoneryhl/VE-ELIN.

pdf bib
Leveraging Generative Large Language Models with Visual Instruction and Demonstration Retrieval for Multimodal Sarcasm Detection
Binghao Tang | Boda Lin | Haolong Yan | Si Li
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Multimodal sarcasm detection aims to identify sarcasm in the given image-text pairs and has wide applications in the multimodal domains. Previous works primarily design complex network structures to fuse the image-text modality features for classification. However, such complicated structures may risk overfitting on in-domain data, reducing the performance in out-of-distribution (OOD) scenarios. Additionally, existing methods typically do not fully utilize cross-modal features, limiting their performance on in-domain datasets. Therefore, to build a more reliable multimodal sarcasm detection model, we propose a generative multimodal sarcasm model consisting of a designed instruction template and a demonstration retrieval module based on the large language model. Moreover, to assess the generalization of current methods, we introduce an OOD test set, RedEval. Experimental results demonstrate that our method is effective and achieves state-of-the-art (SOTA) performance on the in-domain MMSD2.0 and OOD RedEval datasets.

2023

pdf bib
DemoSG: Demonstration-enhanced Schema-guided Generation for Low-resource Event Extraction
Gang Zhao | Xiaocheng Gong | Xinjie Yang | Guanting Dong | Shudong Lu | Si Li
Findings of the Association for Computational Linguistics: EMNLP 2023

Most current Event Extraction (EE) methods focus on the high-resource scenario, which requires a large amount of annotated data and can hardly be applied to low-resource domains. To address EE more effectively with limited resources, we propose the Demonstration-enhanced Schema-guided Generation (DemoSG) model, which benefits low-resource EE from two aspects: Firstly, we propose the demonstration-based learning paradigm for EE to fully use the annotated data, which transforms them into demonstrations to illustrate the extraction process and help the model learn effectively. Secondly, we formulate EE as a natural language generation task guided by schema-based prompts, thereby leveraging label semantics and promoting knowledge transfer in low-resource scenarios. We conduct extensive experiments under in-domain and domain adaptation low-resource settings on three datasets, and study the robustness of DemoSG. The results show that DemoSG significantly outperforms current methods in low-resource scenarios.

2022

pdf bib
Entity-level Interaction via Heterogeneous Graph for Multimodal Named Entity Recognition
Gang Zhao | Guanting Dong | Yidong Shi | Haolong Yan | Weiran Xu | Si Li
Findings of the Association for Computational Linguistics: EMNLP 2022

Multimodal Named Entity Recognition (MNER) faces two specific challenges: 1) How to capture useful entity-related visual information. 2) How to alleviate the interference of visual noise. Previous works have gained progress by improving interacting mechanisms or seeking for better visual features. However, existing methods neglect the integrity of entity semantics and conduct cross-modal interaction at token-level, which cuts apart the semantics of entities and makes non-entity tokens easily interfered with by irrelevant visual noise. Thus in this paper, we propose an end-to-end heterogeneous Graph-based Entity-level Interacting model (GEI) for MNER. GEI first utilizes a span detection subtask to obtain entity representations, which serve as the bridge between two modalities. Then, the heterogeneous graph interacting network interacts entity with object nodes to capture entity-related visual information, and fuses it into only entity-associated tokens to rid non-entity tokens of the visual noise. Experiments on two widely used datasets demonstrate the effectiveness of our method. Our code will be available at https://github.com/GangZhao98/GEI.

pdf bib
Dependency Parsing via Sequence Generation
Boda Lin | Zijun Yao | Jiaxin Shi | Shulin Cao | Binghao Tang | Si Li | Yong Luo | Juanzi Li | Lei Hou
Findings of the Association for Computational Linguistics: EMNLP 2022

Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences.Existing methods for dependency parsing include transition-based method, graph-based method and sequence-to-sequence method.These methods obtain excellent performance and we notice them belong to labeling method.Therefore, it may be very valuable and interesting to explore the possibility of using generative method to implement dependency parsing.In this paper, we propose to achieve Dependency Parsing (DP) via Sequence Generation (SG) by utilizing only the pre-trained language model without any auxiliary structures.We first explore different serialization designing strategies for converting parsing structures into sequences.Then we design dependency units and concatenate these units into the sequence for DPSG.We verify the DPSG is capable of parsing on widely used DP benchmarks, i.e., PTB, UD2.2, SDP15 and SemEval16.In addition, we also investigate the astonishing low-resource applicability of DPSG, which includes unsupervised cross-domain conducted on CODT and few-shot cross-task conducted on SDP15.Our research demonstrates that sequence generation is one of the effective methods to achieve dependency parsing.Our codes are available now.

pdf bib
Simple Tagging System with RoBERTa for Ancient Chinese
Binghao Tang | Boda Lin | Si Li
Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages

This paper describes the system submitted for the EvaHan 2022 Shared Task on word segmentation and part-of-speech tagging for Ancient Chinese. Our system is based on the pre-trained language model SIKU-RoBERTa and the simple tagging layers. Our system significantly outperforms the official baselines in the released test sets and shows the effectiveness.

2021

pdf bib
Multi-Turn Target-Guided Topic Prediction with Monte Carlo Tree Search
Jingxuan Yang | Si Li | Jun Guo
Proceedings of the 18th International Conference on Natural Language Processing (ICON)

This paper concerns the problem of topic prediction in target-guided conversation, which requires the system to proactively and naturally guide the topic thread of the conversation, ending up with achieving a designated target subject. Existing studies usually resolve the task with a sequence of single-turn topic prediction. Greedy decision is made at each turn since it is impossible to explore the topics in future turns under the single-turn topic prediction mechanism. As a result, these methods often suffer from generating sub-optimal topic threads. In this paper, we formulate the target-guided conversation as a problem of multi-turn topic prediction and model it under the framework of Markov decision process (MDP). To alleviate the problem of generating sub-optimal topic thread, Monte Carlo tree search (MCTS) is employed to improve the topic prediction by conducting long-term planning. At online topic prediction, given a target and a start utterance, our proposed MM-TP (MCTS-enhanced MDP for Topic Prediction) firstly performs MCTS to enhance the policy for predicting the topic for each turn. Then, two retrieval models are respectively used to generate the responses of the agent and the user. Quantitative evaluation and qualitative study showed that MM-TP significantly improved the state-of-the-art baselines.

pdf bib
A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech
Jingxuan Yang | Kerui Xu | Jun Xu | Si Li | Sheng Gao | Jun Guo | Nianwen Xue | Ji-Rong Wen
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

In this paper, we present a neural model for joint dropped pronoun recovery (DPR) and conversational discourse parsing (CDP) in Chinese conversational speech. We show that DPR and CDP are closely related, and a joint model benefits both tasks. We refer to our model as DiscProReco, and it first encodes the tokens in each utterance in a conversation with a directed Graph Convolutional Network (GCN). The token states for an utterance are then aggregated to produce a single state for each utterance. The utterance states are then fed into a biaffine classifier to construct a conversational discourse graph. A second (multi-relational) GCN is then applied to the utterance states to produce a discourse relation-augmented representation for the utterances, which are then fused together with token states in each utterance as input to a dropped pronoun recovery layer. The joint model is trained and evaluated on a new Structure Parsing-enhanced Dropped Pronoun Recovery (SPDPR) data set that we annotated with both two types of information. Experimental results on the SPDPR dataset and other benchmarks show that DiscProReco significantly outperforms the state-of-the-art baselines of both tasks.

pdf bib
Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing
Boda Lin | Mingzheng Li | Si Li | Yong Luo
Findings of the Association for Computational Linguistics: EMNLP 2021

Unsupervised cross-domain dependency parsing is to accomplish domain adaptation for dependency parsing without using labeled data in target domain. Existing methods are often of the pseudo-annotation type, which generates data through self-annotation of the base model and performing iterative training. However, these methods fail to consider the change of model structure for domain adaptation. In addition, the structural information contained in the text cannot be fully exploited. To remedy these drawbacks, we propose a Semantics-Structure Adaptative Dependency Parser (SSADP), which accomplishes unsupervised cross-domain dependency parsing without relying on pseudo-annotation or data selection. In particular, we design two feature extractors to extract semantic and structural features respectively. For each type of features, a corresponding feature adaptation method is utilized to achieve domain adaptation to align the domain distribution, which effectively enhances the unsupervised cross-domain transfer capability of the model. We validate the effectiveness of our model by conducting experiments on the CODT1 and CTB9 respectively, and the results demonstrate that our model can achieve consistent performance improvement. Besides, we verify the structure transfer ability of the proposed model by introducing Weisfeiler-Lehman Test.

2020

pdf bib
Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields
Jingxuan Yang | Kerui Xu | Jun Xu | Si Li | Sheng Gao | Jun Guo | Ji-Rong Wen | Nianwen Xue
Findings of the Association for Computational Linguistics: EMNLP 2020

Pronouns are often dropped in Chinese conversations and recovering the dropped pronouns is important for NLP applications such as Machine Translation. Existing approaches usually formulate this as a sequence labeling task of predicting whether there is a dropped pronoun before each token and its type. Each utterance is considered to be a sequence and labeled independently. Although these approaches have shown promise, labeling each utterance independently ignores the dependencies between pronouns in neighboring utterances. Modeling these dependencies is critical to improving the performance of dropped pronoun recovery. In this paper, we present a novel framework that combines the strength of Transformer network with General Conditional Random Fields (GCRF) to model the dependencies between pronouns in neighboring utterances. Results on three Chinese conversation datasets show that the Transformer-GCRF model outperforms the state-of-the-art dropped pronoun recovery models. Exploratory analysis also demonstrates that the GCRF did help to capture the dependencies between pronouns in neighboring utterances, thus contributes to the performance improvements.

2019

pdf bib
A Prism Module for Semantic Disentanglement in Name Entity Recognition
Kun Liu | Shen Li | Daqi Zheng | Zhengdong Lu | Sheng Gao | Si Li
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Natural Language Processing has been perplexed for many years by the problem that multiple semantics are mixed inside a word, even with the help of context. To solve this problem, we propose a prism module to disentangle the semantic aspects of words and reduce noise at the input layer of a model. In the prism module, some words are selectively replaced with task-related semantic aspects, then these denoised word representations can be fed into downstream tasks to make them easier. Besides, we also introduce a structure to train this module jointly with the downstream model without additional data. This module can be easily integrated into the downstream model and significantly improve the performance of baselines on named entity recognition (NER) task. The ablation analysis demonstrates the rationality of the method. As a side effect, the proposed method also provides a way to visualize the contribution of each word.

pdf bib
Recovering dropped pronouns in Chinese conversations via modeling their referents
Jingxuan Yang | Jianzhuo Tong | Si Li | Sheng Gao | Jun Guo | Nianwen Xue
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Pronouns are often dropped in Chinese sentences, and this happens more frequently in conversational genres as their referents can be easily understood from context. Recovering dropped pronouns is essential to applications such as Information Extraction where the referents of these dropped pronouns need to be resolved, or Machine Translation when Chinese is the source language. In this work, we present a novel end-to-end neural network model to recover dropped pronouns in conversational data. Our model is based on a structured attention mechanism that models the referents of dropped pronouns utilizing both sentence-level and word-level information. Results on three different conversational genres show that our approach achieves a significant improvement over the current state of the art.

2018

pdf bib
Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network
Chenliang Li | Weiran Xu | Si Li | Sheng Gao
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Neural network models, based on the attentional encoder-decoder model, have good capability in abstractive text summarization. However, these models are hard to be controlled in the process of generation, which leads to a lack of key information. We propose a guiding generation model that combines the extractive method and the abstractive method. Firstly, we obtain keywords from the text by a extractive model. Then, we introduce a Key Information Guide Network (KIGN), which encodes the keywords to the key information representation, to guide the process of generation. In addition, we use a prediction-guide mechanism, which can obtain the long-term value for future decoding, to further guide the summary generation. We evaluate our model on the CNN/Daily Mail dataset. The experimental results show that our model leads to significant improvements.

pdf bib
From Random to Supervised: A Novel Dropout Mechanism Integrated with Global Information
Hengru Xu | Shen Li | Renfen Hu | Si Li | Sheng Gao
Proceedings of the 22nd Conference on Computational Natural Language Learning

Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural networks for text classification. Unlike the traditional dropout method in which the units are dropped randomly according to the same probability, we aim to use explicit instructions based on global information of the dataset to guide the training process. With GI-Dropout, the model is supposed to pay more attention to inapparent features or patterns. Experiments demonstrate the effectiveness of the dropout with global information on seven text classification tasks, including sentiment analysis and topic classification.

pdf bib
Contextualized Character Representation for Chinese Grammatical Error Diagnosis
Jianbo Zhao | Si Li | Zhiqing Lin
Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications

Nowadays, more and more people are learning Chinese as their second language. Establishing an automatic diagnosis system for Chinese grammatical error has become an important challenge. In this paper, we propose a Chinese grammatical error diagnosis (CGED) model with contextualized character representation. Compared to the traditional model using LSTM (Long-Short Term Memory), our model have better performance and there is no need to add too many artificial features.

2017

pdf bib
N-gram Model for Chinese Grammatical Error Diagnosis
Jianbo Zhao | Hao Liu | Zuyi Bao | Xiaopeng Bai | Si Li | Zhiqing Lin
Proceedings of the 4th Workshop on Natural Language Processing Techniques for Educational Applications (NLPTEA 2017)

Detection and correction of Chinese grammatical errors have been two of major challenges for Chinese automatic grammatical error diagnosis. This paper presents an N-gram model for automatic detection and correction of Chinese grammatical errors in NLPTEA 2017 task. The experiment results show that the proposed method is good at correction of Chinese grammatical errors.

pdf bib
Neural Regularized Domain Adaptation for Chinese Word Segmentation
Zuyi Bao | Si Li | Weiran Xu | Sheng Gao
Proceedings of the 9th SIGHAN Workshop on Chinese Language Processing

For Chinese word segmentation, the large-scale annotated corpora mainly focus on newswire and only a handful of annotated data is available in other domains such as patents and literature. Considering the limited amount of annotated target domain data, it is a challenge for segmenters to learn domain-specific information while avoid getting over-fitted at the same time. In this paper, we propose a neural regularized domain adaptation method for Chinese word segmentation. The teacher networks trained in source domain are employed to regularize the training process of the student network by preserving the general knowledge. In the experiments, our neural regularized domain adaptation method achieves a better performance comparing to previous methods.

2014

pdf bib
Effective Document-Level Features for Chinese Patent Word Segmentation
Si Li | Nianwen Xue
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

2012

pdf bib
SSHLDA: A Semi-Supervised Hierarchical Topic Model
Xian-Ling Mao | Zhao-Yan Ming | Tat-Seng Chua | Si Li | Hongfei Yan | Xiaoming Li
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning

2010

pdf bib
PRIS at Chinese Language Processing
Jiayue Zhang | Yichao Cai | Si Li | Weiran Xu | Jun Guo
CIPS-SIGHAN Joint Conference on Chinese Language Processing