Spain

Commonsense reasoning refers to the ability of evaluating a social situation and acting accordingly. Identification of the implicit causes and effects of a social context is the driving capability which can enable machines to perform commonsense reasoning. The dynamic world of social interactions requires context-dependent on-demand systems to infer such underlying information. However, current approaches in this realm lack the ability to perform commonsense reasoning upon facing an unseen situation, mostly due to incapability of identifying a diverse range of implicit social relations. Hence they fail to estimate the correct reasoning path. In this paper, we present Conditional SEQ2SEQ-based Mixture model (COSMO), which provides us with the capabilities of dynamic and diverse content generation. We use COSMO to generate context-dependent clauses, which form a dynamic Knowledge Graph (KG) on-the-fly for commonsense reasoning. To show the adaptability of our model to context-dependant knowledge generation, we address the task of zero-shot commonsense question answering. The empirical results indicate an improvement of up to +5.2% over the state-of-the-art models.

COLING 2020

COSMO: CONDITIONAL SEQ2SEQ-BASED MIXTURE MODEL FOR ZERO-SHOT COMMONSENSE QUESTION ANSWERING

causality

commonsense reasoning

question answering

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.

poster

We present a novel method for embedding trees in a vector space based on Tensor-Product Representations (TPRs) which allows for inversion: the retrieval of the original tree structure and nodes from the vectorial embedding. Unlike previous attempts, this does not come at the cost of intractable representation size; we utilize a method for non-exact inversion, showing that it works well when there is sufficient randomness in the representation scheme for simple data and providing an upper bound on its error. To handle the huge number of possible tree positions without memoizing position representation vectors, we present a method (Cryptographic Role Embedding) using cryptographic hashing algorithms that allows for the representation of unboundedly many positions. Through experiments on parse tree data, we show a 30,000-dimensional Cryptographic Role Embedding of trees can provide invertibility with error < 1% that previous methods would require 8.6x10^57 dimensions to represent.

Invertible Tree Representations using a Cryptographic Role Embedding Scheme

Natural Language Query interfaces allow the end-users to access the desired information withoutthe need to know any specialized query language, data storage, or schema details. Even withthe recent advances in NLP research space, the state-of-the-art QA systems fall short of under-standing implicit intents of real-world Business Intelligence (BI) queries in enterprise systems asNatural Language Understanding remains an AI-hard problem. We posit that deploying ontologyreasoning over domain semantics can help in achieving better natural language understanding forQA systems. In this paper, we specifically focus on building a Schema Aware Semantic Reason-ing Framework that translates natural language interpretation as a sequence of solvable tasks byan ontology reasoner. We apply our framework on top of an ontology-based, state-of-the-art nat-ural language question-answering system ATHENA, and experiment with 4 benchmarks focusedon BI queries. Our experimental numbers empirically show that the Schema Aware SemanticReasoning indeed helps in achieving significantly better results for handling BI queries with anaverage accuracy improvement of 30%

Paper_2157_COLING_Poster

Social summarization systems become more and more critical with the booming of social media posts like tweets. However, the publicly available large scale social media datasets are rare. Most of existing datasets focus on formal document summarization, while social media texts have many different characteristics from formal documents: 1) Short, 2) Informal, 3) Social signal, 4) Potential relations. In addition, the existing corpus only considers the text on social media, ignoring the potential social signals on social networks, which hinders the use of various social signals in the social media environment. In summary, our contributions are summarized as follows:
(1) Construct an event-oriented social media summarization dataset, TWEETSUM, which is the first summarization dataset that contains user relationships relevant social signals.
(2) Create expert summaries for each social event and verified the existence of sociological theory in real data.
(3) Evaluate the performance of typical extractive summarization models on our
TWEETSUM.

TWEETSUM: Event-oriented Social Summarization Dataset

Summarization is an important natural language processing (NLP) task in identifying key information from text. For conversations, the summarization systems need to extract salient contents from spontaneous utterances by multiple speakers. In a special task-oriented scenario, namely medical conversations between patients and doctors, the symptoms, diagnoses, and treatments could be highly important because the nature of such conversation is to find a medical solution to the problem proposed by the patients. Especially consider that current online medical platforms provide millions of public available conversations between real patients and doctors, where the patients propose their medical problems and the registered doctors offer diagnosis and treatment, a conversation in most cases could be too long and the key information is hard to be located. Therefore, summarizations to the patients' problems and the doctors' treatments in the conversations can be highly useful, in terms of helping other patients with similar problems have a precise reference for potential medical solutions. In this paper, we focus on medical conversation summarization, using a dataset of medical conversations and corresponding summaries which were crawled from a well-known online healthcare service provider in China. We propose a hierarchical encoder-tagger model (HET) to generate summaries by identifying important utterances (with respect to problem proposing and solving) in the conversations. For the particular dataset used in this study, we show that high-quality summaries can be generated by extracting two types of utterances, namely, problem statements and treatment recommendations. Experimental results demonstrate that HET outperforms strong baselines and models from previous studies, and adding conversation-related features can further improve system performance.

Summarizing Medical Conversations via Identifying Important Utterances

We reveal a localness perception problem in Non-Autoregressive Translation (NAT), for which it is difficult to adequately capture source context. To alleviate this problem, we propose to enhance signals of neighbour source tokens into conventional cross-attention. Experimental results on several representative datasets show that our approach can consistently improve translation quality over strong NAT baselines. Extensive analyses demonstrate that the enhanced cross-attention achieves better exploitation of source contexts by leveraging both local and global information.

Context-Aware Cross-Attention for Non-Autoregressive Translation

Previous work for rumor resolution concentrates on exploiting time-series characteristics or modeling topology structure separately. However, how local interactive pattern affects global information assemblage has not been explored. In this paper, we attempt to address the problem by learning evolution of message interaction. We model confrontation and reciprocity between message pairs via discrete variational autoencoders which effectively reflects the diversified opinion interactivity. Moreover, we capture the variation of message interaction using a hierarchical framework to better integrate information flow of a rumor cascade. Experiments on PHEME dataset demonstrate our proposed model achieves higher accuracy than existing methods.

Modeling Evolution of Message Interaction for Rumor Resolution

Data collection for the knowledge graph-to-text generation is expensive. As a result, research on unsupervised models has emerged as an active field recently. However, most unsupervised models have to use non-parallel versions of existing small supervised datasets, which largely constrain their potential.
In this paper, we propose a large-scale, general-domain dataset, GenWiki. Our unsupervised dataset has 1.3M text and graph examples, respectively. With a human-annotated test set, we provide this new benchmark dataset for future research on unsupervised text generation from knowledge graphs.

GenWiki: A Dataset of 1.3 Million Content-Sharing Text and Graphs for Unsupervised Graph-to-Text Generation

We present a transfer learning system to perform a mixed Spanish-English sentiment classification task. Our proposal uses the state-of-the-art language model BERT and embed it within a ULMFiT transfer learning pipeline. This combination allows us to predict the polarity detection of code-mixed (English-Spanish) tweets. Thus, among 29 submitted systems, our approach (referred to as dplominop) is ranked 4th on the Sentimix Spanglish test set of SemEval 2020 Task 9. In fact, our system yields the weighted-F1 score value of 0.755 which can be easily reproduced --- the source code and implementation details are made available.

Robust System based on Transformer for Code-Mixed Sentiment Classification

Fine-tuning of pre-trained transformer networks such as BERT yield state-of-the-art results for text classification tasks. Typically, fine-tuning is performed on task-specific training datasets in a supervised manner. One can also fine-tune in unsupervised manner beforehand by further pretraining the masked language modeling (MLM) task. Hereby, in-domain data for unsupervised MLM resembling the actual classification target dataset allows for domain adaptation of the model. In this paper, we compare current pre-trained transformer networks with and without MLM fine-tuning on their performance for offensive language detection. Our MLM fine-tuned RoBERTa-based classifier officially ranks 1st in the SemEval 2020 Shared Task 12 for the English language. Further experiments with the ALBERT model even surpass this result.

Fine-Tuning of Pre-Trained Transformer Networks for Offensive Language Detection

This paper describes our system to assess humour intensity in edited news headlines as part of a participation in the 7th task of SemEval-2020 on ``Humor, Emphasis and Sentiment". Various factors need to be accounted for in order to assess the funniness of an edited headline. We propose an architecture that uses hand-crafted features, knowledge bases and a language model to understand humour, and combines them in a regression model. Our system outperforms two baselines. In general, automatic humour assessment remains a difficult task.

Downloads

Next from COLING 2020

Invertible Tree Representations using a Cryptographic Role Embedding Scheme

Similar lecture

BioMedBERT: A Pre-trained Biomedical Language Model for QA and IR

.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

Invertible Tree Representations using a Cryptographic Role Embedding Scheme

Similar lecture

BioMedBERT: A Pre-trained Biomedical Language Model for QA and IR

Downloads