Compressing Large-Scale Transformer-Based Models: A Case Study on BERT

Transformer-based models pre-trained on large-scale corpora achieve state-of-the-art accuracy for natural language processing tasks, but are too resource-hungry and compute-intensive to suit low-capability devices or applications with strict latency requirements. One potential remedy is model compression, which has attracted extensive attention. This paper summarizes the branches of research on compressing Transformers, focusing on the especially popular BERT model. BERT's complex architecture means that a compression technique that is highly effective on one part of the model, e.g., attention layers, may be less successful on another part, e.g., fully connected layers. In this systematic study, we identify the state of the art in compression for each part of BERT, clarify current best practices for compressing large-scale Transformer models, and provide insights into the inner workings of various methods. Our categorization and analysis also shed light on promising future research directions for achieving a lightweight, accurate, and generic natural language processing model.

CheckThat! at CLEF 2020: Enabling the Automatic Identification and Verification of Claims in Social Media

We describe the third edition of the CheckThat! Lab, which is part of the 2020 Cross-Language Evaluation Forum (CLEF). CheckThat! proposes four complementary tasks and a related task from previous lab editions, offered in English, Arabic, and Spanish. Task 1 asks to predict which tweets in a Twitter stream are worth fact-checking. Task 2 asks to determine whether a claim posted in a tweet can be verified using a set of previously fact-checked claims. Task 3 asks to retrieve text snippets from a given set of Web pages that would be useful for verifying a target tweet's claim. Task 4 asks to predict the veracity of a target tweet's claim using a set of Web pages and potentially useful snippets in them. Finally, the lab offers a fifth task that asks to predict the check-worthiness of the claims made in English political debates and speeches. CheckThat! features a full evaluation framework. The evaluation is carried out using mean average precision or precision at rank k for ranking tasks, and F1 for classification tasks.

A Context-Aware Approach for Detecting Check-Worthy Claims in Political Debates

In the context of investigative journalism, we address the problem of automatically identifying which claims in a given document are most worthy and should be prioritized for fact-checking. Despite its importance, this is a relatively understudied problem. Thus, we create a new dataset of political debates, containing statements that have been fact-checked by nine reputable sources, and we train machine learning models to predict which claims should be prioritized for fact-checking, i.e., we model the problem as a ranking task. Unlike previous work, which has looked primarily at sentences in isolation, in this paper we focus on a rich input representation modeling the context: relationship between the target statement and the larger context of the debate, interaction between the opponents, and reaction by the moderator and by the public. Our experiments show state-of-the-art results, outperforming a strong rivaling system by a margin, while also confirming the importance of the contextual information.

Proppy: A System to Unmask Propaganda in Online News

We present proppy, the first publicly available real-world, real-time propaganda detection system for online news, which aims at raising awareness, thus potentially limiting the impact of propaganda and helping fight disinformation. The system constantly monitors a number of news sources, deduplicates and clusters the news into events, and organizes the articles about an event on the basis of the likelihood that they contain propagandistic content. The system is trained on known propaganda sources using a variety of stylistic features. The evaluation results on a standard dataset show state-of-the-art results for propaganda detection.

SemEval-2013 Task 2: Sentiment Analysis in Twitter

In recent years, sentiment analysis in social media has attracted a lot of research interest and has been used for a number of applications. Unfortunately, research has been hindered by the lack of suitable datasets, complicating the comparison between approaches. To address this issue, we have proposed SemEval-2013 Task 2: Sentiment Analysis in Twitter, which included two subtasks: A, an expression-level subtask, and B, a message-level subtask. We used crowdsourcing on Amazon Mechanical Turk to label a large Twitter training dataset along with additional test sets of Twitter and SMS messages for both subtasks. All datasets used in the evaluation are released to the research community. The task attracted significant interest and a total of 149 submissions from 44 teams. The best-performing team achieved an F1 of 88.9% and 69% for subtasks A and B, respectively.

Machine Translation Evaluation Meets Community Question Answering

We explore the applicability of machine translation evaluation (MTE) methods to a very different problem: answer ranking in community Question Answering. In particular, we adopt a pairwise neural network (NN) architecture, which incorporates MTE features, as well as rich syntactic and semantic embeddings, and which efficiently models complex non-linear interactions. The evaluation results show state-of-the-art performance, with sizeable contribution from both the MTE features and from the pairwise NN architecture.

SemEval-2014 Task 9: Sentiment Analysis in Twitter

We describe the Sentiment Analysis in Twitter task, ran as part of SemEval-2014. It is a continuation of the last year's task that ran successfully as part of SemEval-2013. As in 2013, this was the most popular SemEval task; a total of 46 teams contributed 27 submissions for subtask A (21 teams) and 50 submissions for subtask B (44 teams). This year, we introduced three new test sets: (i) regular tweets, (ii) sarcastic tweets, and (iii) LiveJournal sentences. We further tested on (iv) 2013 tweets, and (v) 2013 SMS messages. The highest F1-score on (i) was achieved by NRC-Canada at 86.63 for subtask A and by TeamX at 70.96 for subtask B.

Pairwise Neural Machine Translation Evaluation

We present a novel framework for machine translation evaluation using neural networks in a pairwise setting, where the goal is to select the better translation from a pair of hypotheses, given the reference translation. In this framework, lexical, syntactic and semantic information from the reference and the two hypotheses is compacted into relatively small distributed vector representations, and fed into a multi-layer neural network that models the interaction between each of the hypotheses and the reference, as well as between the two hypotheses. These compact representations are in turn based on word and sentence embeddings, which are learned using neural networks. The framework is flexible, allows for efficient learning and classification, and yields correlation with humans that rivals the state of the art.

SemEval-2015 Task 10: Sentiment Analysis in Twitter

In this paper, we describe the 2015 iteration of the SemEval shared task on Sentiment Analysis in Twitter. This was the most popular sentiment analysis shared task to date with more than 40 teams participating in each of the last three years. This year's shared task competition consisted of five sentiment prediction subtasks. Two were reruns from previous years: (A) sentiment expressed by a phrase in the context of a tweet, and (B) overall sentiment of a tweet. We further included three new subtasks asking to predict (C) the sentiment towards a topic in a single tweet, (D) the overall sentiment towards a topic in a set of tweets, and (E) the degree of prior polarity of a phrase.

Towards Constructing a Corpus for Studying the Effects of Treatments and Substances Reported in PubMed Abstracts

We present the construction of an annotated corpus of PubMed abstracts reporting about positive, negative or neutral effects of treatments or substances. Our ultimate goal is to annotate one sentence (rationale) for each abstract and to use this resource as a training set for text classification of effects discussed in PubMed abstracts. Currently, the corpus consists of 750 abstracts. We describe the automatic processing that supports the corpus construction, the manual annotation activities and some features of the medical language in the abstracts selected for the annotated corpus. It turns out that recognizing the terminology and the abbreviations is key for determining the rationale sentence. The corpus will be applied to improve our classifier, which currently has accuracy of 78.80% achieved with normalization of the abstract terms based on UMLS concepts from specific semantic groups and an SVM with a linear kernel. Finally, we discuss some other possible applications of this corpus.