Previous studies on multi-party dialogue generation predominantly concentrated on modeling the reply-to structure of dialogue histories, always overlooking the coherence between generated responses and target utterances. To address this issue, we propose a Reinforcement Learning approach emphasizing both Topic and Rhetorical Coherence (RL-TRC). In particular, the topic- and rhetorical-coherence tasks are designed to enhance the model’s perception of coherence with the target utterance. Subsequently, an agent is employed to learn a coherence policy, which guides the generation of responses that are topically and rhetorically aligned with the target utterance. Furthermore, three discourse-aware rewards are developed to assess the coherence between the generated response and the target utterance, with the objective of optimizing the policy. The experimental results and in-depth analyses on two popular datasets demonstrate that our RL-TRC significantly outperforms the state-of-the-art baselines, particularly in generating responses that are more coherent with the target utterances.
Although existing fashionable generation methods on Incomplete Utterance Rewriting (IUR) can generate coherent utterances, they often result in the inclusion of irrelevant and redundant tokens in rewritten utterances due to their inability to focus on critical tokens in dialogue context. Furthermore, the limited size of the training datasets also contributes to the insufficient training of the IUR model. To address the first issue, we propose a multi-task learning framework EO-IUR (Editing Operation-guided Incomplete Utterance Rewriting) that introduces the editing operation labels generated by sequence labeling module to guide generation model to focus on critical tokens. Furthermore, we introduce a token-level heterogeneous graph to represent dialogues. To address the second issue, we propose a two-dimensional utterance augmentation strategy, namely editing operation-based incomplete utterance augmentation and LLM-based historical utterance augmentation. The experimental results on three datasets demonstrate that our EO-IUR outperforms previous state-of-the-art (SOTA) baselines in both open-domain and task-oriented dialogue.
Topic segmentation and outline generation strive to divide a document into coherent topic sections and generate corresponding subheadings, unveiling the discourse topic structure of a document. Compared with sentence-level topic structure, the paragraph-level topic structure can quickly grasp and understand the overall context of the document from a higher level, benefitting many downstream tasks such as summarization, discourse parsing, and information retrieval. However, the lack of large-scale, high-quality Chinese paragraph-level topic structure corpora restrained relative research and applications. To fill this gap, we build the Chinese paragraph-level topic representation, corpus, and benchmark in this paper. Firstly, we propose a hierarchical paragraph-level topic structure representation with three layers to guide the corpus construction. Then, we employ a two-stage man-machine collaborative annotation method to construct the largest Chinese Paragraph-level Topic Structure corpus (CPTS), achieving high quality. We also build several strong baselines, including ChatGPT, to validate the computability of CPTS on two fundamental tasks (topic segmentation and outline generation) and preliminarily verified its usefulness for the downstream task (discourse parsing).
Large language models, like ChatGPT, have shown remarkable capability in many downstream tasks, yet their ability to understand discourse structures of dialogues remains less explored, where it requires higher level capabilities of understanding and reasoning. In this paper, we aim to systematically inspect ChatGPT’s performance in two discourse analysis tasks: topic segmentation and discourse parsing, focusing on its deep semantic understanding of linear and hierarchical discourse structures underlying dialogue. To instruct ChatGPT to complete these tasks, we initially craft a prompt template consisting of the task description, output format, and structured input. Then, we conduct experiments on four popular topic segmentation datasets and two discourse parsing datasets. The experimental results showcase that ChatGPT demonstrates proficiency in identifying topic structures in general-domain conversations yet struggles considerably in specific-domain conversations. We also found that ChatGPT hardly understands rhetorical structures that are more complex than topic structures. Our deeper investigation indicates that ChatGPT can give more reasonable topic structures than human annotations but only linearly parses the hierarchical rhetorical structures. In addition, we delve into the impact of in-context learning (e.g., chain-of-thought) on ChatGPT and conduct the ablation study on various prompt components, which can provide a research foundation for future work. The code is available at https://github.com/yxfanSuda/GPTforDDA.
Document-level Event Factuality Identification (DEFI) refers to identifying the degree of certainty that a specific event occurs in a document. Previous studies on DEFI failed to link the document-level event factuality with various sentence-level factuality values in the same document. In this paper, we innovatively propose an event factuality inference task to bridge the sentence-level and the document-level event factuality semantically. Specifically, we present a Sentence-to-Document Inference Network (SDIN) that contains a multi-layer interaction module and a gated aggregation module to integrate the above two tasks, and employ a multi-task learning framework to improve the performance of DEFI. The experimental results on the public English and Chinese DLEF datasets show that our model outperforms the SOTA baselines significantly.
Most neural abstractive summarization models are capable of producing high-quality summaries. However, they still frequently contain factual errors. Existing factuality-oriented abstractive summarization models only consider the integration of factual information and ignore the causes of factual errors. To address this issue, we propose a factuality-oriented abstractive summarization model DASum, which is based on a new task factual relation discrimination that is able to identify the causes of factual errors. First, we use data augmentation methods to construct counterfactual summaries (i. e., negative samples), and build a factual summarization dataset. Then, we propose the factual relation discrimination task, which determines the factuality of the dependency relations in summaries during summary generation and guides our DASum to generate factual relations, thereby improving the factuality of summaries. Experimental results on the CNN/DM and XSUM datasets show that our DASum outperforms several state-of-the-art benchmarks in terms of the factual metrics.
Cross-document event coreference resolution (CD-ECR) is a task of clustering event mentions across multiple documents that refer to the same real-world events. Previous studies usually model the CD-ECR task as a pairwise similarity comparison problem by using different event mention features, and consider the highly similar event mention pairs in the same cluster as coreferent. In general, most of them only consider the local context of event mentions and ignore their implicit global information, thus failing to capture the interactions of long-distance event mentions. To address the above issue, we regard discourse structure as global information to further improve CD-ECR. First, we use a discourse rhetorical structure constructor to construct tree structures to represent documents. Then, we obtain shortest dependency paths from the tree structures to represent interactions between event mention pairs. Finally, we feed the above information to a multi-layer perceptron to capture the similarities of event mention pairs for resolving coreferent events. Experimental results on the ECB+ dataset show that our proposed model outperforms several baselines and achieves the competitive performance with the start-of-the-art baselines.
Dialogue discourse parsing aims to reflect the relation-based structure of dialogue by establishing discourse links according to discourse relations. To alleviate data sparsity, previous studies have adopted multitasking approaches to jointly learn dialogue discourse parsing with related tasks (e.g., reading comprehension) that require additional human annotation, thus limiting their generality. In this paper, we propose a multitasking framework that integrates dialogue discourse parsing with its neighboring task addressee recognition. Addressee recognition reveals the reply-to structure that partially overlaps with the relation-based structure, which can be exploited to facilitate relation-based structure learning. To this end, we first proposed a reinforcement learning agent to identify training examples from addressee recognition that are most helpful for dialog discourse parsing. Then, a task-aware structure transformer is designed to capture the shared and private dialogue structure of different tasks, thereby further promoting dialogue discourse parsing. Experimental results on both the Molweni and STAC datasets show that our proposed method can outperform the SOTA baselines. The code will be available at https://github.com/yxfanSuda/RLTST.
Event coreference resolution (ECR) aims to group event mentions referring to the same real-world event into clusters. Most previous studies adopt the “encoding first, then scoring” framework, making the coreference judgment rely on event encoding. Furthermore, current methods struggle to leverage human-summarized ECR rules, e.g., coreferential events should have the same event type, to guide the model. To address these two issues, we propose a prompt-based approach, CorefPrompt, to transform ECR into a cloze-style MLM (masked language model) task. This allows for simultaneous event modeling and coreference discrimination within a single template, with a fully shared context. In addition, we introduce two auxiliary prompt tasks, event-type compatibility and argument compatibility, to explicitly demonstrate the reasoning process of ECR, which helps the model make final predictions. Experimental results show that our method CorefPrompt performs well in a state-of-the-art (SOTA) benchmark.
Event coreference resolution (ECR) aims to cluster event mentions that refer to the same real-world events. Deep learning methods have achieved SOTA results on the ECR task. However, due to the encoding length limitation, previous methods either adopt classical pairwise models based on sentence-level context or split each document into multiple chunks and encode them separately. They failed to capture the interactions and contextual cues among those long-distance event mentions. Besides, high-level information, such as event topics, is rarely considered to enhance representation learning for ECR. To address the above two issues, we first apply a Longformer-based encoder to obtain the document-level embeddings and an encoder with a trigger-mask mechanism to learn sentence-level embeddings based on local context. In addition, we propose an event topic generator to infer the latent topic-level representations. Finally, using the above event embeddings, we employ a multiple tensor matching method to capture their interactions at the document, sentence, and topic levels. Experimental results on the KBP 2017 dataset show that our model outperforms the SOTA baselines.
Conversational discourse parsing aims to construct an implicit utterance dependency tree to reflect the turn-taking in a multi-party conversation. Existing works are generally divided into two lines: graph-based and transition-based paradigms, which perform well for short-distance and long-distance dependency links, respectively. However, there is no study to consider the advantages of both paradigms to facilitate conversational discourse parsing. As a result, we propose a distance-aware multi-task framework DAMT that incorporates the strengths of transition-based paradigm to facilitate the graph-based paradigm from the encoding and decoding process. To promote multi-task learning on two paradigms, we first introduce an Encoding Interactive Module (EIM) to enhance the flow of semantic information between both two paradigms during the encoding step. And then we apply a Distance-Aware Graph Convolutional Network (DAGCN) in the decoding process, which can incorporate the different-distance dependency links predicted by the transition-based paradigm to facilitate the decoding of the graph-based paradigm. The experimental results on the datasets STAC and Molweni show that our method can significantly improve the performance of the SOTA graph-based paradigm on long-distance dependency links.
Extracting spatial relations from texts is a fundamental task for natural language understanding and previous studies only regard it as a classification task, ignoring those spatial relations with null roles due to their poor information. To address the above issue, we first view spatial relation extraction as a generation task and propose a novel hybrid model HMCGR for this task. HMCGR contains a generation and a classification model, while the former can generate those null-role relations and the latter can extract those non-null-role relations to complement each other. Moreover, a reflexivity evaluation mechanism is applied to further improve the accuracy based on the reflexivity principle of spatial relation. Experimental results on SpaceEval show that HMCGR outperforms the SOTA baselines significantly.
Most previous work on temporal relation extraction only focused on extracting the temporal relations among events or suffered from the issue of different expressions of events, timexes and Document Creation Time (DCT). Moreover, DCT can act as a hub to semantically connect the other events and timexes in a document. Unfortunately, previous work cannot benefit from such critical information. To address the above issues, we propose a unified DCT-centered Temporal Relation Extraction model DTRE to identify the relations among events, timexes and DCT. Specifically, sentence-style DCT representation is introduced to address the first issue and unify event expressions, timexes and DCT. Then, a DCT-aware graph is applied to obtain their contextual structural representations. Furthermore, a DCT-anchoring multi-task learning framework is proposed to jointly predict three types of temporal relations in a batch. Finally, we apply a DCT-guided global inference to further enhance the global consistency among different relations. Experimental results on three datasets show that our DTRE outperforms several SOTA baselines on E-E, E-T and E-D significantly.
Document-level Event Factuality Identification (DEFI) predicts the factuality of a specific event based on a document from which the event can be derived, which is a fundamental and crucial task in Natural Language Processing (NLP). However, most previous studies only considered sentence-level task and did not adopt document-level knowledge. Moreover, they modelled DEFI as a typical text classification task depending on annotated information heavily, and limited to the task-specific corpus only, which resulted in data scarcity. To tackle these issues, we propose a new framework formulating DEFI as Machine Reading Comprehension (MRC) tasks considering both Span-Extraction (Ext) and Multiple-Choice (Mch). Our model does not employ any other explicit annotated information, and utilizes Transfer Learning (TL) to extract knowledge from universal large-scale MRC corpora for cross-domain data augmentation. The empirical results on DLEFM corpus demonstrate that the proposed model outperforms several state-of-the-arts.
Automatic Essay Scoring (AES) is the task of using the computer to evaluate the quality of essays automatically. Current research on AES focuses on scoring the overall quality or single trait of prompt-specific essays. However, the users not only expect to obtain the overall score but also the instant feedback from different traits to help their writing in the real world. Therefore, we first annotate a mutli-trait dataset ACEA including 1220 argumentative essays from four traits, i.e., essay organization, topic, logic, and language. And then we design a hierarchical multi-task trait scorer HMTS to evaluate the quality of writing by modeling these four traits. Moreover, we propose an inter-sequence attention mechanism to enhance information interaction between different tasks and design the trait-specific features for various tasks in AES. The experimental results on ACEA show that our HMTS can effectively score essays from multiple traits, outperforming several strong models.
Implicit discourse relation recognition (IDRR) is a critical task in discourse analysis. Previous studies only regard it as a classification task and lack an in-depth understanding of the semantics of different relations. Therefore, we first view IDRR as a generation task and further propose a method joint modeling of the classification and generation. Specifically, we propose a joint model, CG-T5, to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. Furthermore, we design three target sentence forms, including the question form, for the generation model to incorporate prior knowledge. To address the issue that large discourse units are hardly embedded into the target sentence, we also propose a target sentence construction mechanism that automatically extracts core sentences from those large discourse units. Experimental results both on Chinese MCDTB and English PDTB datasets show that our model CG-T5 achieves the best performance against several state-of-the-art systems.
Discourse structure tree construction is the fundamental task of discourse parsing and most previous work focused on English. Due to the cultural and linguistic differences, existing successful methods on English discourse parsing cannot be transformed into Chinese directly, especially in paragraph level suffering from longer discourse units and fewer explicit connectives. To alleviate the above issues, we propose two reading modes, i.e., the global backward reading and the local reverse reading, to construct Chinese paragraph level discourse trees. The former processes discourse units from the end to the beginning in a document to utilize the left-branching bias of discourse structure in Chinese, while the latter reverses the position of paragraphs in a discourse unit to enhance the differentiation of coherence between adjacent discourse units. The experimental results on Chinese MCDTB demonstrate that our model outperforms all strong baselines.
Due to its great importance in deep natural language understanding and various down-stream applications, text-level parsing of discourse rhetorical structure (DRS) has been drawing more and more attention in recent years. However, all the previous studies on text-level discourse parsing adopt bottom-up approaches, which much limit the DRS determination on local information and fail to well benefit from global information of the overall discourse. In this paper, we justify from both computational and perceptive points-of-view that the top-down architecture is more suitable for text-level DRS parsing. On the basis, we propose a top-down neural architecture toward text-level DRS parsing. In particular, we cast discourse parsing as a recursive split point ranking task, where a split point is classified to different levels according to its rank and the elementary discourse units (EDUs) associated with it are arranged accordingly. In this way, we can determine the complete DRS as a hierarchical tree structure via an encoder-decoder with an internal stack. Experimentation on both the English RST-DT corpus and the Chinese CDTB corpus shows the great effectiveness of our proposed top-down approach towards text-level DRS parsing.
In the literature, most of the previous studies on English implicit discourse relation recognition only use sentence-level representations, which cannot provide enough semantic information in Chinese due to its unique paratactic characteristics. In this paper, we propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations. In particular, besides encoding arguments (discourse units) using a gated convolutional network to obtain sentence-level representations, we train a simplified topic model to infer the latent topic-level representations. Moreover, we feed the two pairs of representations to two factored tensor networks, respectively, to capture both the sentence-level interactions and topic-level relevance using multi-slice tensors. Experimentation on CDTB, a Chinese discourse corpus, shows that our proposed model significantly outperforms several state-of-the-art baselines in both micro and macro F1-scores.
Document-level event factuality identification is an important subtask in event factuality and is crucial for discourse understanding in Natural Language Processing (NLP). Previous studies mainly suffer from the scarcity of suitable corpus and effective methods. To solve these two issues, we first construct a corpus annotated with both document- and sentence-level event factuality information on both English and Chinese texts. Then we present an LSTM neural network based on adversarial training with both intra- and inter-sequence attentions to identify document-level event factuality. Experimental results show that our neural network model can outperform various baselines on the constructed corpus.
The task of nuclearity recognition in Chinese discourse remains challenging due to the demand for more deep semantic information. In this paper, we propose a novel text matching network (TMN) that encodes the discourse units and the paragraphs by combining Bi-LSTM and CNN to capture both global dependency information and local n-gram information. Moreover, it introduces three components of text matching, the Cosine, Bilinear and Single Layer Network, to incorporate various similarities and interactions among the discourse units. Experimental results on the Chinese Discourse TreeBank show that our proposed TMN model significantly outperforms various strong baselines in both micro-F1 and macro-F1.
In view of the differences between the annotations of micro and macro discourse rela-tionships, this paper describes the relevant experiments on the construction of the Macro Chinese Discourse Treebank (MCDTB), a higher-level Chinese discourse corpus. Fol-lowing RST (Rhetorical Structure Theory), we annotate the macro discourse information, including discourse structure, nuclearity and relationship, and the additional discourse information, including topic sentences, lead and abstract, to make the macro discourse annotation more objective and accurate. Finally, we annotated 720 articles with a Kappa value greater than 0.6. Preliminary experiments on this corpus verify the computability of MCDTB.
Previous studies on temporal relation extraction focus on mining sentence-level information or enforcing coherence on different temporal relation types among various event mentions in the same sentence or neighboring sentences, largely ignoring those discourse-level temporal relations in nonadjacent sentences. In this paper, we propose a discourse-level global inference model to mine those temporal relations between event mentions in document-level, especially in nonadjacent sentences. Moreover, we provide various kinds of discourse-level constraints, which derived from event semantics, to further improve our global inference model. Evaluation on a Chinese corpus justifies the effectiveness of our discourse-level global inference model over two strong baselines.