Spain

Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni&#39;s source samples from the Ubuntu Chat Corpus, including 10,000 dialogs comprising 88,303 utterances. We annotate 30,066 questions on this corpus, including both answerable and unanswerable questions. Molweni also uniquely contributes discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT; Asher et al., 2016) style for all of its multiparty dialogs, contributing large-scale (78,245 annotated discourse relations) data to bear on the task of multiparty dialog discourse parsing. Our experiments show that Molweni is a challenging dataset for current MRC models: BERT-wwm, a current, strong SQuAD 2.0 performer, achieves only 67.7% F1 on Molweni&#39;s questions, a 20+% significant drop as compared against its SQuAD 2.0 performance.

COLING 2020

Molweni: A Challenge Multiparty Dialogue-based Machine Reading Comprehension Dataset with Discourse Structure

multiparty dialogue

machine reading comprehension

discourse parsing

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

Research into the area of multiparty dialog has grown considerably over recent years. We present the Molweni dataset, a machine reading comprehension (MRC) dataset with discourse structure built over multiparty dialog. Molweni's source samples from the Ubuntu Chat Corpus, including 10,000 dialogs comprising 88,303 utterances. We annotate 30,066 questions on this corpus, including both answerable and unanswerable questions. Molweni also uniquely contributes discourse dependency annotations in a modified Segmented Discourse Representation Theory (SDRT; Asher et al., 2016) style for all of its multiparty dialogs, contributing large-scale (78,245 annotated discourse relations) data to bear on the task of multiparty dialog discourse parsing. Our experiments show that Molweni is a challenging dataset for current MRC models: BERT-wwm, a current, strong SQuAD 2.0 performer, achieves only 67.7% F1 on Molweni's questions, a 20+% significant drop as compared against its SQuAD 2.0 performance.

poster

Script learning aims to predict the subsequent event according to the existing event chain. Recent studies focus on event co-occurrence to solve this problem. However, few studies integrate external event knowledge to solve this problem. With our observations, external event knowledge can provide additional knowledge like temporal or causal knowledge for understanding event chain better and predicting the right subsequent event. In this work, we integrate event knowledge
from ASER (Activities, States, Events and their Relations) knowledge base to help predict the next event. We propose a new approach consisting of knowledge retrieval stage and knowledge integration stage. In the knowledge retrieval stage, we select relevant external event knowledge from ASER. In the knowledge integration stage, we propose three methods to integrate external knowledge into our model and infer final answers. Experiments on the widely-used MultiChoice Narrative Cloze (MCNC) task show our approach achieves state-of-the-art performance compared to other methods.

Integrating External Event Knowledge for Script Learning

Sentiment analysis provides a useful overview of customer review contents. Many review websites allow a user to enter a summary in addition to a full review. Intuitively, summary information may give additional benefit for review sentiment analysis. In this paper, we conduct a study to exploit methods for better use of summary information. We start by finding out that the sentimental signal distribution of a review and that of its corresponding summary are in fact complementary to each other. We thus explore various architectures to better guide the interactions between the two and propose a hierarchically-refined review-centric attention model. Empirical results show that our review-centric model can make better use of user-written summaries for review sentiment analysis, and is also more effective compared to existing methods when the user summary is replaced with summary generated by an automatic summarization system.

Making the Best Use of Review Summary for Sentiment Analysis

Event extraction (EE) plays an important role in real-life applications, such as information retrieval and news summarization. It aims to discover events with triggers and their corresponding arguments. Typically, EE contains several subtasks: trigger identification, trigger classification, event argument identification, and argument role classification. Most existing work follows a pipelined manner or uses a joint structure but is pipelined in essence. As a result, these efforts fail to utilize information interactions among event triggers, event arguments, and argument roles, which causes information redundancy. In this paper, we propose to exploit the role information of the arguments in an event and devise a Hierarchical Policy Network (HPNet) to perform joint EE. The whole EE process is fulfilled through a two-level hierarchical structure consisting of two policy networks for event detection and argument detection. The deep information interactions among the subtasks are realized, and it is more natural to deal with multiple events issue. 


Joint Event Extraction with Hierarchical Policy Network

We present a multi-level alignment pretraining method in a unified architecture for multi-lingual semantic parsing. In this architecture, we use an adversarial training method to align the space of different languages and use sentence level and word level parallel corpus as supervision information to align the semantic of different languages. Finally, we jointly train the multi-level alignment and semantic parsing tasks. We conduct experiments on a publicly avail-able multi-lingual semantic parsing dataset ATIS and a newly constructed dataset. Experimental results show that our model outperforms state-of-the-art methods on both datasets.


Multi-level Alignment Pretraining for Multi-lingual Semantic Parsing

Open-domain reading comprehension is a challenging issue in terms of natural language understanding. In this paper, we proposes a miscellaneous-context-based
method to convert a sentence into a knowledge embedding in the form of a directed graph. Based on the idea of conceptual graphs, this graph representation method
abbreviated as AGG-CG can (1) accommodate the slot-filling challenges in typical question answering, (2) access to the sentence-level graph structure in order to explicitly capture the neighbouring connections of reference concept nodes, and (3) project an edge of a sentence-level graph to the space of semantic relevance with respect to the corresponding concept nodes, by cooperating with the semantics-measured module. In conclusion, our approach is the first towards the interpretable process of learning human-comprehensible graphical representations with the experimental evidence.

Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs

• Companies are racing to leverage digital technologies (AI, IoT,
Cloud, among others)
•Majority of companies report that their strategies did not deliver
anticipated business results
• We used NLP to understand the different clusters of digital
strategy patterns of Fortune 500 companies
• Results showed four approaches to digital strategy
• The results provided a baseline to improve our understanding of
digital strategy approaches

Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls

Sparsity is regarded as a desirable property of representations, especially in terms of explanation. However, its usage has been limited due to the gap with dense representations. Most NLP re- search progresses in recent years are based on dense representations. Thus the desirable property of sparsity cannot be leveraged. Inspired by Fourier Transformation, in this paper, we propose a novel Semantic Transformation method to bridge the dense and sparse spaces, which can facilitate the NLP research to shift from dense space to sparse space or to jointly use both spaces. Experiments using classification tasks and natural language inference task show that the proposed Semantic Transformation is effective.


Transformation of Dense and Sparse Text Representations

Multimodal named entity recognition (MNER) for tweets has received increasing attention recently. Most of the multimodal methods used attention mechanisms to capture the text-related visual information. However, unrelated or weakly related text-image pairs account for a large proportion in tweets. Visual clues unrelated to the text would incur uncertain or even negative effects for multimodal model learning. In this paper, we propose a novel pre-trained multimodal model based on Relationship Inferring and Visual Attention (RIVA) for tweets. The RIVA model controls the attention-based visual clues with a gate regarding the role of image to the semantics of text. We use a teacher-student semi-supervised paradigm to leverage a large unlabeled multimodal tweet corpus with a labeled data set for text-image relation classification. In the multimodal NER task, the experimental results show the significance of text-related visual features for the visual-linguistic model and our approach achieves SOTA performance on the MNER datasets.

RIVA: A Pre-trained Tweet Multimodal Model Based on Text-image Relationship for Multimodal NER

Understanding neural models is a major topic of interest in the deep learning community. In this paper, we propose to interpret a general neural model comparatively. Specifically, we study the sequence-to-sequence (Seq2Seq) model in the contexts of two mainstream NLP tasks–machine translation and dialogue response generation–as they both use the Seq2Seq model. We investigate how the two tasks are different and how their task difference results in major differences in the behaviors of the resulting translation and dialogue generation systems. This study allows us to make several interesting observations and gain valuable insights, which can be used to help develop better translation and dialogue generation models. To our knowledge, no such comparative study has been done so far.

Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling


Annotating data is trivial in real-world situations. To solve this problem, Active Learning has been well-studied to decrease the needed amount of the annotating data and successfully applied to NLU on some pipeline model. However, no research has been done on investigating how the relation information between intents and slots can improve the efficiency of AL algorithms. Therefore, we propose a pool-based multitask active learning framework for NLU and an efficient computation for the entropy of a joint model. Experiment results show that our framework is efficient and has the potential for industrial use.

Molweni: A Challenge Multiparty Dialogue-based Machine Reading Comprehension Dataset with Discourse Structure

Downloads

Next from COLING 2020

Integrating External Event Knowledge for Script Learning

Similar lecture

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

Molweni: A Challenge Multiparty Dialogue-based Machine Reading Comprehension Dataset with Discourse Structure

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from COLING 2020

Integrating External Event Knowledge for Script Learning

Similar lecture

Learn with Noisy Data via Unsupervised Loss Correction for Weakly Supervised Reading Comprehension

Downloads