Thailand

Encoder pre-training is promising in end-to-end Speech Translation (ST), given the fact that speech-to-translation data is scarce.
But ST encoders are not simple instances of Automatic Speech Recognition (ASR) or Machine Translation (MT) encoders.
For example, we find that ASR encoders lack the global context representation, which is necessary for translation, whereas MT encoders are not designed to deal with long but locally attentive acoustic sequences.
In this work, we propose a Stacked Acoustic-and-Textual Encoding (SATE) method for speech translation.
Our encoder begins with processing the acoustic sequence as usual, but later behaves more like an MT encoder for a global representation of the input sequence.
In this way, it is straightforward to incorporate the pre-trained models into the system.
Also, we develop an adaptor module to alleviate the representation inconsistency between the pre-trained ASR encoder and MT encoder, and develop a multi-teacher knowledge distillation method to preserve the pre-training knowledge.
Experimental results on the LibriSpeech En-Fr and MuST-C En-De ST tasks show that our method achieves state-of-the-art BLEU scores of 18.3 and 25.2.
To our knowledge, we are the first to develop an end-to-end ST system that achieves comparable or even better BLEU performance than the cascaded ST counterpart when large-scale ASR and MT data is available.

IJCNLP-AACL 2021

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders

adaptor

end-to-end speech translation

pre-training

**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).

technical paper

Sentence embedding methods using natural language inference (NLI) datasets have been successfully applied to various tasks.
However, these methods are only available for limited languages due to relying heavily on the large NLI datasets.
In this paper, we propose DefSent, a sentence embedding method that uses definition sentences from a word dictionary, which performs comparably on unsupervised semantics textual similarity (STS) tasks and slightly better on SentEval tasks than conventional methods.
Since dictionaries are available for many languages, DefSent is more broadly applicable than methods using NLI datasets without constructing additional datasets.
We demonstrate that DefSent performs comparably on unsupervised semantics textual similarity (STS) tasks and slightly better on SentEval tasks to the methods using large NLI datasets.
Our code is publicly available at https://github.com/hpprc/defsent.

DefSent: Sentence Embeddings using Definition Sentences

Document-level contextual information has shown benefits to text-based machine translation, but whether and how context helps end-to-end (E2E) speech translation (ST) is still under-studied. We fill this gap through extensive experiments using a simple concatenation-based context-aware ST model, paired with adaptive feature selection on speech encodings for computational efficiency. We investigate several decoding approaches, and introduce in-model ensemble decoding which jointly performs document- and sentence-level translation using the same model. Our results on the MuST-C benchmark with Transformer demonstrate the effectiveness of context to E2E ST. Compared to sentence-level ST, context-aware ST obtains better translation quality (+0.18-2.61 BLEU), improves pronoun and homophone translation, shows better robustness to (artificial) audio segmentation errors, and reduces latency and flicker to deliver higher quality for simultaneous translation.

Beyond Sentence-Level End-to-End Speech Translation: Context Helps

Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make it better capture the cross-modality interaction in the pre-training stage. Meanwhile, it also integrates a spatial-aware self-attention mechanism into the Transformer architecture so that the model can fully understand the relative positional relationship among different text blocks. Experiment results show that LayoutLMv2 outperforms LayoutLM by a large margin and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including FUNSD (0.7895 to 0.8420), CORD (0.9493 to 0.9601), SROIE (0.9524 to 0.9781), Kleister-NDA (0.8340 to 0.8520), RVL-CDIP (0.9443 to 0.9564), and DocVQA (0.7295 to 0.8672).

LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding

Existed pre-training methods either focus on single-modal tasks or multi-modal tasks, and cannot effectively adapt to each other. They can only utilize single-modal data (i.e., text or image) or limited multi-modal data (i.e., image-text pairs). In this work, we propose a UNIfied-MOdal pre-training architecture, namely UNIMO, which can effectively adapt to both single-modal and multi-modal understanding and generation tasks. Large scale of free text corpus and image collections are utilized to improve the capability of visual and textual understanding, and cross-modal contrastive learning (CMCL) is leveraged to align the textual and visual information into a unified semantic space, over a corpus of image-text pairs augmented with related images and texts. With the help of rich non-paired single-modal data, our model is able to learn more generalizable representations, by allowing textual knowledge and visual knowledge to enhance each other in the unified semantic space. The experimental results show that UNIMO greatly improves the performance of several single-modal and multi-modal downstream tasks. Our code and pre-trained models are public at \url{https://github.com/PaddlePaddle/Research/tree/master/NLP/UNIMO}.

UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning

Multimodal fusion has been proved to improve emotion recognition performance in previous works.
However, in real-world applications, we often encounter the problem of missing modality, and which modalities will be missing is uncertain. It makes the fixed multimodal fusion fail in such cases.
In this work, we propose a unified model, Missing Modality Imagination Network (MMIN), to deal with the uncertain missing modality problem. MMIN learns robust joint multimodal representations, which can predict the representation of any missing modality given available modalities under different missing modality conditions.Comprehensive experiments on two benchmark datasets demonstrate that the unified MMIN model significantly improves emotion recognition performance under both uncertain missing-modality testing conditions and full-modality ideal testing condition. The code will be available at https://github.com/AIM3-RUC/MMIN.

Missing Modality Imagination Network for Emotion Recognition with Uncertain Missing Modalities

object discovery and segmentation, notably MONet and Slot Attention. While these algorithms learn an object-centric representation just by reconstructing the input image, LORL enables them to further learn to associate the learned representations to concepts, i.e., words for object categories, properties, and spatial relationships, from language input. These object-centric concepts derived from language facilitate the learning of object-centric representations. LORL can be integrated with various unsupervised object discovery algorithms that are language-agnostic. Experiments show that the integration of LORL consistently improves the performance of unsupervised object discovery methods on two datasets via the help of language. We also show that concepts learned by LORL, in conjunction with object discovery methods, aid downstream tasks such as referring expression comprehension.

Language-Mediated, Object-Centric Representation Learning

Enthusiasm plays an important role in engaging communication. It enables speakers to be distinguished and remembered, creating an emotional bond that inspires and motivates their addressees to act, listen, and coordinate (Bettencourt et al., 1983). Although people can easily identify enthusiasm, this is a rather difficult task for machines due to the lack of resources and models that can help them understand or generate enthusiastic behavior. 
We introduce Entheos, the first multimodal dataset for studying enthusiasm composed of video, audio, and text. We present several baseline models and an ablation study using different features, showing the importance of pitch, loudness, and discourse relation parsing in distinguishing enthusiastic communication.

Entheos: {A} Multimodal Dataset for Studying Enthusiasm

Previous studies have argued that pre-trained language models encode commonsense relational knowledge (e.g. that apples are edible). However, simultaneous work has revealed that such models are often insensitive to context, even ignoring overt contextual cues such as negations. In this paper, we investigate whether masked language models (the BERT family), can move beyond naive associative biases (e.g., apple -> edible) when the context warrants (e.g. ranking inedible higher when presented with the information that the apple is rotten). We introduce the WinoVenti procedure, which adversarially exploits associative biases in masked language models to create model-specific Winograd-style entailment schemas. Using our constructed WinoVenti challenges set of over 2000 schemas, we discover that language models in the BERT family experience a steep drop in performance on prompts that require them to pick answers which require reasoning about context (e.g., from 89.8% to 18.4% for BERT Large). We present evidence to show that language models exhibit different associative biases, suggesting a need for future work in developing and analyzing frameworks similar to WinoVenti that are tuned to model-specific weaknesses.

Are Rotten Apples Edible? Challenging Commonsense Inference Ability with Exceptions

Retrofitting is a technique used to move word vectors closer together or further apart in their space to reflect their relationships in a Knowledge Base (KB). However, retrofitting only works on concepts that are present in that KB. RetroGAN uses a pair of Generative Adversarial Networks (GANs) to learn a one-to-one mapping between concepts and their
retrofitted counterparts. It applies that mapping (post-specializes) to handle concepts that
do not appear in the original KB in a manner similar to how some natural language systems handle out-of-vocabulary entries. We test our system on three word-similarity benchmarks and a downstream sentence simplification task, and achieve the state of the art (CARD-660). Altogether, our results demonstrate our system’s effectiveness for out-of-knowledge and rare word generalization.

RetroGAN: A Cyclic Post-Specialization System for Improving Out-of-Knowledge and Rare Word Representations

The task of ICD coding is to automatically extract International Classification of Diseases (ICD) codes from unstructured clinical notes or discharge summaries, which not only saves time and money but also reduces errors. Although several studies are proposed to solve this challenging task, none of them distinguishes the importance of different phrases with a word window. Intuitively, informative phrases should be more useful for the prediction. In this paper, we propose a simple yet effective feature compressed ICD coding model named Fusion to address this issue. In particular, we propose a novel attentive soft-pooling approach to compress the sparse and redundant word representations into informative and dense ones as local features. Besides, we use the key-query attention mechanism for modeling the inner relations among local features to generate the global features, which are further used to predict ICD codes. Experiments on two widely used datasets demonstrate that the proposed model outperforms baselines. However, on the MIMIC-III Full dataset, we find that none of the state-of-the-art approaches significantly perform better than others. Thus, automated ICD coding is still a challenging task.

Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders

Downloads

Next from IJCNLP-AACL 2021

DefSent: Sentence Embeddings using Definition Sentences

Similar lecture

SemFace: Pre-training Encoder and Decoder with a Semantic Interface for Neural Machine Translation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES