Thailand

Despite recent successes of large pre-trained language models in solving reasoning tasks, their inference capabilities remain opaque. We posit that such models can be made more interpretable by explicitly generating interim inference rules, and using them to guide the generation of task-specific textual outputs. In this paper we present \textsc{Coins}, a recursive inference framework that i) iteratively reads context sentences, ii) dynamically generates contextualized inference rules, encodes them, and iii) uses them to guide task-specific output generation. We apply \COINS\ to a \textit{Narrative Story Completion} task that asks a model to complete a story with missing sentences, to produce a coherent story with plausible logical connections, causal relationships, and temporal dependencies. By modularizing inference and sentence generation steps in a recurrent model, we aim to make reasoning steps and their effects on next sentence generation transparent. Our automatic and manual evaluations show that the model generates better story sentences than SOTA baselines, especially in terms of coherence. We further demonstrate improved performance over strong pre-trained LMs in generating commonsense inference rules. The recursive nature of \COINS\ holds the potential for controlled generation of longer sequences.

ACL-IJCNLP 2021

COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion

commonsense reasoning

story generation

inference

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

poster

In this paper, we evaluate the translation of negation both automatically and manually, in English—German (EN—DE) and English—Chinese (EN—ZH). We show that the ability of neural machine translation (NMT) models to translate negation has improved with deeper and more advanced networks, although the performance varies between language pairs and translation directions. The accuracy of manual evaluation in EN—DE, DE—EN, EN—ZH, and ZH—EN is 95.7%, 94.8%, 93.4%, and 91.7%, respectively. In addition, we show that under-translation is the most significant error type in NMT, which contrasts with the more diverse error profile previously observed for statistical machine translation. To better understand the root of the under-translation of negation, we study the model's information flow and training data. While our information flow analysis does not reveal any deficiencies that could be used to detect or fix the under-translation of negation, we find that negation is often rephrased during training, which could make it more difficult for the model to learn a reliable link between source and target negation. We finally conduct intrinsic analysis and extrinsic probing tasks on negation, showing that NMT models can distinguish negation and non-negation tokens very well and encode a lot of information about negation in hidden states but nevertheless leave room for improvement.

Revisiting Negation in Neural Machine Translation

Reranking models enable the integration of rich features to select a better output hypothesis within an n-best list or lattice. These models have a long history in NLP, and we revisit discriminative reranking for modern neural machine translation models by training a large transformer architecture. This takes as input both the source sentence as well as a list of hypotheses to output a ranked list. The reranker is trained to predict the observed distribution of a desired metric, e.g. BLEU, over the n-best list. Since such a discriminator contains hundreds of millions of parameters, we improve its generalization using pre-training and data augmentation techniques. Experiments on four WMT directions show that our discriminative reranking approach is effective and complementary to existing generative reranking approaches, yielding improvements of up to 4 BLEU over the beam search output.

Discriminative Reranking for Neural Machine Translation

High-performing machine translation (MT) systems can help overcome language barriers while making it possible for everyone to communicate and use language technologies in the language of their choice. However, such systems require large amounts of parallel sentences for training, and translators can be difficult to find and expensive. Here, we present a data collection strategy for MT which, in contrast, is cheap and simple, as it does not require bilingual speakers. Based on the insight that humans pay specific attention to movements, we use graphics interchange formats (GIFs) as a pivot to collect parallel sentences from monolingual annotators. We use our strategy to collect data in Hindi, Tamil and English. As a baseline, we also collect data using images as a pivot. We perform an intrinsic evaluation by manually evaluating a subset of the sentence pairs and an extrinsic evaluation by finetuning mBART (Liu et al., 2020) on the collected data. We find that sentences collected via GIFs are indeed of higher quality.

Don't Rule Out Monolingual Speakers: A Method For Crowdsourcing Machine Translation Data

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence representations are proved to be collapsed and thus produce a poor performance on the semantic textual similarity (STS) tasks. In this paper, we present ConSERT, a Contrastive Framework for Self-Supervised SEntence Representation Transfer, that adopts contrastive learning to fine-tune BERT in an unsupervised and effective way. By making use of unlabeled texts, ConSERT solves the collapse issue of BERT-derived sentence representations and make them more applicable for downstream tasks. Experiments on STS datasets demonstrate that ConSERT achieves an 8% relative improvement over the previous state-of-the-art, even comparable to the supervised SBERT-NLI. And when further incorporating NLI supervision, we achieve new state-of-the-art performance on STS tasks. Moreover, ConSERT obtains comparable results with only 1000 samples available, showing its robustness in data scarcity scenarios.

ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Social spambots, an emerging class of spammers attempting to emulate people, are difficult for both human annotators and classic bot detection techniques to reliably distinguish from genuine accounts. We examine this human emulation through studying the human characteristics (personality, gender, age, emotions) exhibited by social spambots' language, hypothesizing the values for these attributes will be unhuman-like (e.g. unusually high or low). We found our hypothesis mostly disconfirmed --- individually, social bots exhibit very human-like attributes. However, a striking pattern emerged when consider the full distributions of these estimated human attributes: social bots were extremely similar and average in their expressed personality, demographics, and emotion (in contrast with traditional bots which we found to exhibit more variance and extreme values than genuine accounts). We thus consider how well social bots can be identified only using the 17 variables of these human attributes and ended up with a new state of the art in social spambot detection (e.g. F1 = .946). Further, simulating the situation of not knowing the bots \textit{a priori}, we found that even an unsupervised clustering using the same 17 attributes could yield nearly as accurate of social bot identification (F1 = 0.925).

Characterizing Social Spambots by their Human Traits

In this poster/presentation, we present the event detection models and systems we have developed for Multilingual Protest News Detection - SharedTask 1 at CASE 2021. The shared task has 4 subtasks which cover event detection at different granularity levels (from document level to token level) and across multiple languages (English, Hindi, Portuguese and Spanish). To handle data from multiple languages, we use a multilingual transformer-based language model (XLM-R) as the input text encoder. We apply a variety of techniques and build several transformer-based models that perform consistently well across all the sub-tasks and languages. Our systems achieve anaverage F1 score of 81.2. Out of thirteen subtask-language tracks, our submissions rank 1st in nine and 2nd in four tracks.

IBM MNLP IE at CASE 2021 Task 1: Multigranular and Multilingual Event Detection on Protest News

An ever-increasing amount of text, in the form of social media posts and news articles, gives rise to new challenges and opportunities for the automatic extraction of socio-political events. In this paper, we present our submission to the Shared Tasks on Socio-Political and Crisis Events Detection, Task 1, Multilingual Protest News Detection, Subtask 2, Event Sentence Classification, of CASE @ ACL-IJCNLP 2021. In our submission, we utilize the RoBERTa model with additional pretraining, and achieve the best F1 score of 0.8532 in event sentence classification in English and the second-best F1 score of 0.8700 in Portuguese via simple translation. We analyze the failure cases of our model. We also conduct an ablation study to show the effect of choosing the right pretrained language model, adding additional training data and data augmentation.

Team “NoConflict” at CASE 2021 Task 1: Pretraining for Sentence-Level Protest Event Detection

An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches improved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and exploration-exploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgment.

WeaSuLπ: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue

The paper proposes a template-guided pointer network mechanism for task-oriented dialogue systems. The system retrieves a collection of candidate answers from a conversation repository which are used as templates to generate the system's response. The approach harnesses the idea that similar types of inputs have outputs of similar structure with a few changes. Experimental results on several dialogue tasks, both real and artificial, show that our approach performs well.

A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems

This paper presents a learning assistant that tests one's knowledge and gives feedback that helps a person learn at a faster pace.
A learning assistant based on an automated question generation has extensive uses in education, information websites, self-assessment, FAQs, testing ML agents, research, etc. Multiple researchers, and companies have worked on Virtual Assistance, but majorly in English. Our work covers the fundamental question forms with question types: adjective, yes/no, adverb, verb, when, where, whose, quotative, and quantitative (how many/how much). We constructed rules for question generation using Part of Speech (POS) tags and Universal Dependency (UD) tags along with linguistic information of the surrounding relevant context of the word. 
Our system is primarily built on question generation in Telugu, and is also capable of evaluating the user's answers to the generated questions.

COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion

Downloads

Next from ACL-IJCNLP 2021

Revisiting Negation in Neural Machine Translation

Similar lecture

Analyzing Stereotypes in Generative Text Inference Tasks