Spain

We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are based on the original Transformer architecture (Vaswani et al., 2017) but consist of two decoders, each responsible for one task (ASR or ST). Our major contribution lies in how these decoders interact with each other: one decoder can attend to different information sources from the other via a dual-attention mechanism. We propose two variants of these architectures corresponding to two different levels of dependencies between the decoders, called the parallel and cross dual-decoder Transformers, respectively. Extensive experiments on the MuST-C dataset show that our models outperform the previously-reported highest translation performance in the multilingual settings, and outperform as well bilingual one-to-one results. Furthermore, our parallel models demonstrate no trade-off between ASR and ST compared to the vanilla multi-task architecture. Our code and pre-trained models are available at https://github.com/formiel/speech-translation.

COLING 2020

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation

dual-decoder

speech translation

multilingual

transformer

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.

technical paper

We propose a new self-explainable model for Natural Language Processing (NLP) text classification tasks. Our approach constructs explanations concurrently with the formulation of classification predictions. To do so, we extract a rationale from the text, then use it to predict a concept of interest as the final prediction. We provide three types of explanations: 1) rationale extraction, 2) a measure of feature importance, and 3) clustering of concepts. In addition, we show how our model can be compressed without applying complicated compression techniques. We experimentally demonstrate our explainability approach on a number of well-known text classification datasets.

RANCC: Rationalizing Neural Networks via Concept Clustering

We investigate the impact of political ideology biases in training data. Through a set of comparison studies, we examine the propagation of biases in several widely-used NLP models and its effect on the overall retrieval accuracy. Our work highlights the susceptibility of large, complex models to propagating the biases from human-selected input, which may lead to a deterioration of retrieval accuracy, and the importance of controlling for these biases. Finally, as a way to mitigate the bias, we propose to learn a text representation that is invariant to political ideology while still judging topic relevance.

Inflating Topic Relevance with Ideology: A Case Study of Political Ideology Bias in Social Topic Detection Models

While internalized “implicit knowledge” in pretrained transformers has led to fruitful progress in many natural language understanding tasks, how to most effectively elicit such knowledge remains an open question. Based on the text-to-text transfer transformer (T5) model, this work explores a template-based approach to extract implicit knowledge for commonsense reasoning on multiple-choice (MC) question answering tasks. Experiments on three representative MC datasets show the surprisingly good performance of our simple template, coupled with a logit normalization technique for disambiguation. Furthermore, we verify that our proposed template can be easily extended to other MC tasks with contexts such as supporting facts in open-book question answering settings. Starting from the MC task, this work initiates further research to find generic natural language templates that can effectively leverage stored knowledge in pretrained models.

Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models

Next generation virtual assistants are envisioned to handle multimodal inputs (e.g., vision, memories of previous interactions, and the user's utterances), and perform multimodal actions (e.g., displaying a route while generating the system's utterance).

We introduce Situated Interactive MultiModal Conversations (SIMMC) as a new direction aimed at training agents that take multimodal actions grounded in a co-evolving multimodal input context in addition to the dialog history.

We provide two SIMMC datasets totalling 13K human-human dialogs (169K utterances) collected using a multimodal Wizard-of-Oz (WoZ) setup, on two shopping domains: (a) furniture -- grounded in a shared virtual environment; and (b) fashion -- grounded in an evolving set of images. Datasets include multimodal context of the items appearing in each scene, and contextual NLU, NLG and coreference annotations using a novel and unified framework of SIMMC conversational acts for both user and assistant utterances.

Finally, we present several tasks within SIMMC as objective evaluation protocols, such as structural API prediction, response generation, and dialog state tracking. We benchmark a collection of existing models on these SIMMC tasks as strong baselines, and demonstrate rich multimodal conversational interactions.

Our data, annotations, and models are publicly available (https://github.com/facebookresearch/simmc).

Situated and Interactive Multimodal Conversations

General purpose relation extraction has recently seen considerable gains in part due to a massively data-intensive distant supervision technique from Soares et al. (2019) that produces state-of-the-art results across many benchmarks. In this work, we present a methodology for collecting high quality training data for relation extraction from unlabeled text that achieves a near-recreation of their zero-shot and few-shot results at a fraction of the training cost. Our approach exploits the predictable distributional structure of date-marked news articles to build a denoised corpus – the extraction process filters out low quality examples. We show that a smaller multilingual encoder trained on this corpus performs comparably to the current state-of-the-art (when both receive little to no fine-tuning) on few-shot and standard relation benchmarks in English and Spanish despite using many fewer examples (50k vs. 300mil+).

Event-Guided Denoising for Multilingual Relation Learning

We introduce a deep learning model to learn the set of enumerated job skills associated with a job description. In our analysis of a large-scale government job portal mycareersfuture.sg, we observe that as much as 65% of job descriptions miss describing a significant number of relevant skills. Our model addresses this task from the perspective of an extreme multi-label classification (XMLC) problem, where descriptions are the evidence for the binary relevance of thousands of individual skills. Building upon the current state-of-the-art language modeling approaches such as BERT, we show our XMLC method improves on an existing baseline solution by over 9% and 7% absolute improvements in terms of recall and normalized discounted cumulative gain. 

We further show that our approach effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings by taking into account the structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process. To facilitate future research and replication of our work, we have made the dataset and the implementation of our model publicly available.

Retrieving Skills from Job Description: A Language Model Based Extreme Multi-label Classification Framework

Analogy is assumed to be the cognitive mechanism speakers resort to in order to inflect an unknown form of a lexeme based on knowledge of other words in a language. In this process, an analogy is formed between word forms within an inflectional paradigm but also across paradigms. As neural network models for inflection are typically trained only on lemma-target form pairs, we propose three new ways to provide neural models with additional source forms to strengthen analogy-formation, and compare our methods to other approaches in the literature. We show that the proposed methods of providing a Transformer sequence-to-sequence model with additional analogy sources in the input are consistently effective, and improve upon recent state-of-the-art results on 46 languages, particularly in low-resource settings. We also propose a method to combine the analogy-motivated approach with data hallucination or augmentation. We find that the two approaches are complementary to each other and combining the two approaches is especially helpful when the training data is extremely limited.

Analogy Models for Neural Word Inflection

Although the Indonesian language is spoken by almost 200 million people and the 10th most spoken language in the world, it is under-represented in NLP research. Previous work on Indonesian has been hampered by a lack of annotated datasets, a sparsity of language resources, and a lack of resource standardization. In this work, we release the IndoLEM dataset comprising seven tasks for the Indonesian language, spanning morpho-syntax, semantics, and discourse. We additionally release IndoBERT, a new pre-trained language model for Indonesian, and evaluate it over IndoLEM, in addition to benchmarking it against existing resources. Our
experiments show that IndoBERT achieves state-of-the-art performance over most of the tasks in IndoLEM.

IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP

The presentation is about paper, RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion. In this paper, we propose a relation-adaptive translation function built upon a novel weighted product in complex space, where the weights are learnable, relation-specific and independent to embedding size. Based on the function, we then present our Relation-adaptive translating Embedding (RatE) approach to score each graph triple. Moreover, a novel negative sampling method is proposed to utilize both prior knowledge and self-adversarial learning for effective optimization. Experiments verify RatE achieves state-of-the-art performance on four link prediction benchmarks.

RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion

Transformer-based language models achieve high performance on various tasks, but we still lack understanding of the kind of linguistic knowledge they learn and rely on. We evaluate three models (BERT, RoBERTa, and ALBERT), testing their grammatical and semantic knowledge by sentence-level probing, diagnostic cases, and masked prediction tasks. We focus on relative clauses (in American English) as a complex phenomenon needing contextual information and antecedent identification to be resolved. Based on a naturalistic dataset, probing shows that all three models indeed capture linguistic knowledge about grammaticality, achieving high performance.Evaluation on diagnostic cases and masked prediction tasks considering fine-grained linguistic knowledge, however, shows pronounced model-specific weaknesses especially on semantic knowledge, strongly impacting models’ performance. Our results highlight the importance of (a)model comparison in evaluation task and (b) building up claims of model performance and the linguistic knowledge they capture beyond purely probing-based evaluations.

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation

Downloads

Next from COLING 2020

RANCC: Rationalizing Neural Networks via Concept Clustering

Similar lecture

Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation

.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

RANCC: Rationalizing Neural Networks via Concept Clustering

Similar lecture

Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus

Downloads