Spain

We take a close look at a recent dataset of TED-talks annotated with the questions they implicitly evoke, TED-Q (Westera et al., 2020). We test to what extent the relation between a discourse and the questions it evokes is merely one of similarity or association, as opposed to deeper semantic/pragmatic interpretation. We do so by turning the TED-Q dataset into a binary classification task, constructing an analogous task from explicit questions we extract from the BookCorpus (Zhu et al., 2015), and fitting a BERT-based classifier alongside models based on different notions of similarity. The BERT-based classifier, achieving close to human performance, outperforms all similarity-based models, suggesting that there is more to identifying true evoked questions than plain similarity.


COLING 2020

Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions

question anticipation

question under discussion

implicit question

similarity

discourse

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 introduce a new set of benchmark datasets derived from ACLED data for fine-grained event classification and compare the performance of various state-of-the-art machine learning models on these datasets, including SVM based on TF-IDF character n-grams and neural context-free embeddings (GLOVE and FASTTEXT) as well as deep learning-based BERT with its contextual embeddings. The best results in terms of micro (94.3-94.9%) and macro F1 (86.0-88.9%) were obtained using BERT transformer, with simpler TF-IDF character n-gram based SVM being an interesting alternative. Further, we discuss the pros and cons of the considered benchmark models in terms of their robustness and the dependence of the classification performance on the size of training data.

New Benchmark Corpus and Models for Fine-grained Event Classification: To BERT or not to BERT?

Automatically generated stories should be not only coherent, but also interesting. Thus apart from realizing a story line, the text also have to include rich details to engage the readers. We propose a model that features two different generation components: (1) an outliner, which proceeds the main story line to establish global coherence; and (2) a detailer, which supplies relevant details to the story in a locally coherent manner. Human evaluation show that our model substantially improves the informativeness of generated text while retaining its coherence, outperforming a number of baselines.

Story Generation with Rich Details

The ability to change a person’s mind on a given issue depends both on the arguments they are presented with and on their underlying perspectives and biases on that issue. Predicting stance changes requires characterizing both aspects and the interaction between them, especially in realistic settings in which stance changes are very rare. We suggest a modular learning approach, which decomposes the task into multiple modules, focusing on different aspects of the interaction between users, their beliefs, and the arguments

Predicting Stance Change Using Modular Architectures

Meetings are essential to modern organizations. Numerous meetings are held and recorded daily, more than can ever be comprehended. A meeting summarization system that identifies salient utterances from the transcripts to automatically generate meeting minutes can help. It empowers users to rapidly search and sift through large meeting collections. To date, the impact of domain terminology on the performance of meeting summarization remains understudied, despite that meetings are rich with domain knowledge. In this paper, we create gold-standard annotations for domain terminology on a sizable meeting corpus; they are known as jargon terms. We then analyze the performance of a meeting summarization system with and without jargon terms. Our findings reveal that domain terminology can have a substantial impact on summarization performance. We publicly release all domain terminology to advance research in meeting summarization.

How Domain Terminology Affects Meeting Summarization Performance

We propose a simple method for nominal coordination boundary identification. As the main strength of our method, it can identify the coordination boundary without training on labeled data, and can be applied even if coordination structure annotations are not available. Our system employs pre-trained word embeddings to measure the similarities of words and detects the span of coordination, assuming that conjuncts share syntactic and semantic similarities. We demonstrate that our method yields good results in identifying coordinated noun phrases in the GENIA corpus and is comparable to a recent supervised method for the case when the coordinator conjoins simple noun phrases.

Coordination Boundary Identification without Labeled Data for Compound Terms Disambiguation

The widespread adoption of reference-based automatic evaluation metrics such as ROUGE has promoted the development of document summarization. In this paper, we consider a new protocol for designing reference-based metrics that require the endorsement of source document(s). Following protocol, we propose an anchored ROUGE metric fixing each summary particle on source document, which bases the computation on more solid ground. Empirical results on benchmark datasets validate that source document helps to induce a higher correlation with human judgments for ROUGE metric. Being self-explanatory and easy-to-implement, the protocol can naturally foster various effective designs of reference-based metrics besides the anchored ROUGE introduced here.

An Anchor-Based Automatic Evaluation Metric for Document Summarization

HTML is usually discarded in free text Web NER, even though it is intuitively useful for entity delimitation. 
We ask to what extent the inclusion of HTML tags in free text sentences affects NER performance, which Web pages might benefit the most and how HTML tags might be included efficiently in sentence-based NER.

Leveraging HTML in Free Text Web Named Entity Recognition

As smart speakers and conversational robots become ubiquitous, the demand for expressive speech synthesis has increased. In this paper, to control the emotional parameters of the speech synthesis according to certain dialogue contents, we construct a news dataset with emotion labels ("positive," "negative," or "neutral") annotated for each sentence. We then propose a method to identify emotion labels using a model combining BERT and BiLSTM-CRF, and evaluate its effectiveness using the constructed dataset. The results showed that the classification model performance can be efficiently improved by preferentially annotating news articles with low confidence in the human-in-the-loop machine learning framework.

Sentiment Analysis for Emotional Speech Synthesis in a News Dialogue System

Learning semantic correspondences between structured input data (e.g., slot-value pairs) and associated texts is a core problem for many downstream NLP applications, e.g., data-to-text generation. 
Large-scale datasets recently proposed for generation contain loosely corresponding data text pairs, where part of spans in text cannot be aligned to its incomplete paired input. 
To learn semantic correspondences from such datasets, we propose a two-stage local-to-global alignment (L2GA) framework. First, a local model based on multi-instance learning is applied to build alignments for texts spans that can be directly grounded to its paired structured input. Then, a novel global model built upon a memory-guided conditional random field (CRF) layer aims to infer missing alignments for text spans not supported by paired incomplete inputs, where the memory is designed to leverage alignment clues provided by the local model to strengthen the global model. In this way, the local model and global model can work jointly to learn semantic correspondences in the same framework. Experimental results show that our proposed method can be generalized to both restaurant and computer domains and improve the alignment accuracy.

Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments

Existing models for data-to-text tasks generate fluent but sometimes incorrect sentences e.g., “Nikkei gains” is generated when “Nikkei drops” is expected. We investigate models trained on contrastive examples, that is, incorrect sentences or terms, in addition to correct ones to reduce such errors. We first create rules to produce contrastive examples from correct ones by replacing frequent crucial terms such as “gain” or “drop”. We then use learning methods with several losses that exploit contrastive examples. Experiments on the market comment generation task show that 1) exploiting contrastive examples improves the capability to generate sentences with better lexical choices, without degrading the fluency, 2) the choice of the loss function is an important factor because the performances of different metrics depend on the types of loss functions, and 3) the use of the examples produced by some specific rules further improves performance. Human evaluation also supports the effectiveness of using contrastive examples.

Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions

Downloads

Next from COLING 2020

New Benchmark Corpus and Models for Fine-grained Event Classification: To BERT or not to BERT?

Similar lecture

A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations

Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions

.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

New Benchmark Corpus and Models for Fine-grained Event Classification: To BERT or not to BERT?

Similar lecture

A Large-Scale Corpus of E-mail Conversations with Standard and Two-Level Dialogue Act Annotations

Downloads