Thailand

better social inclusion. Large multidisciplinary projects showed promising steps in that direction. Since 2010, the field started attracting more attention but at the cost of major shifts in system architecture, target audience, and evaluation strategies. Somewhere along the way, the focus has shifted from ATS for social good towards building complex end-to-end neural architectures that are not aimed at any particular target population. This study presents the trajectory of ATS for social good, the main issues in current ATS trends, and the ways forward that could bring the field back to its initial goals.

ACL-IJCNLP 2021

Automatic Text Simplification for Social Good: Progress and Challenges

text simplification; nlp for social good; accessibility

**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

In Machine Translation, assessing the quality of a large amount of automatic translations can be challenging. Automatic metrics are not reliable when it comes to high performing systems. In addition, resorting to human evaluators can be expensive, especially when evaluating multiple systems. 
To overcome the latter challenge, we propose a novel application of online learning that, given an ensemble of Machine Translation systems, dynamically converges to the best systems, by taking advantage of the human feedback available. 
Our experiments on WMT'19 datasets show that our online approach quickly converges to the top-3 ranked systems for the language pairs considered, despite the lack of human feedback for many translations.

Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort

In this work, we provide a systematic and comprehensive empirical comparison of pretrained multilingual language models versus their monolingual counterparts with regard to their monolingual task performance. We study a set of nine typologically diverse languages with readily available pretrained monolingual models on a set of five diverse monolingual downstream tasks. We first aim to establish, via fair and controlled comparisons, if a gap between the multilingual and the corresponding monolingual representation of that language exists, and subsequently investigate the reason for any performance difference. To disentangle conflating factors, we train new monolingual models on the same data, with monolingually and multilingually trained tokenizers. We find that while the pretraining data size is an important factor, a designated monolingual tokenizer plays an equally important role in the downstream performance. Our results show that languages that are adequately represented in the multilingual model's vocabulary exhibit negligible performance decreases over their monolingual counterparts. We further find that replacing the original multilingual tokenizer with the specialized monolingual tokenizer improves the downstream performance of the multilingual model for almost every task and language.

How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models

Cross-lingual transfer has improved greatly through multi-lingual language model pretraining, reducing the need for parallel data and increasing absolute performance. However, this progress has also brought to light the differences in performance across languages. Specifically, certain language families and typologies seem to consistently perform worse in these models. In this paper, we address what effects morphological typology has on zero-shot cross-lingual transfer for two tasks: Part-of-speech tagging and sentiment analysis. We perform experiments on 19 languages from four language typologies (fusional, isolating, agglutinative, and introflexive) and find that transfer to another morphological type generally implies a higher loss than transfer to another language with the same morphological typology. Furthermore, POS tagging is more sensitive to morphological typology than sentiment analysis and, on this task, models perform much better on fusional languages than on the other typologies.

Evaluating morphological typology in zero-shot cross-lingual transfer

Generating code-switched text is a problem of growing interest, especially given the scarcity of corpora containing large volumes of real code-switched text. In this work, we adapt a state-of-the-art neural machine translation model to generate Hindi-English code-switched sentences starting from monolingual Hindi sentences. We outline a carefully designed curriculum of pretraining steps, including the use of synthetic code-switched text, that enable the model to generate high-quality code-switched text. Using text generated from our model as data augmentation, we show significant reductions in perplexity on a language modeling task, compared to using text from other generative models of CS text. We also show improvements using our text for a downstream code-switched natural language inference task. Our generated text is further subjected to a rigorous evaluation using a human evaluation study and a range of objective metrics, where we show performance comparable (and sometimes even superior) to code-switched text obtained via crowd workers who are native Hindi speakers.

From Machine Translation to Code-Switching: Generating High-Quality Code-Switched Text

It is generally believed that a translation memory (TM) should be beneficial for machine translation tasks. Unfortunately, existing wisdom demonstrates the superiority of TM-based neural machine translation (NMT) only on the TM-specialized translation tasks rather than general tasks, with a non-negligible computational overhead. In this paper, we propose a fast and accurate approach to TM-based NMT within the Transformer framework: the model architecture is simple and employs a single bilingual sentence as its TM, leading to efficient training and inference; and its parameters are effectively optimized through a novel training criterion. Extensive experiments on six TM-specialized tasks show that the proposed approach substantially surpasses several strong baselines that use multiple TMs, in terms of BLEU and running time. In particular, the proposed approach also advances the strong baselines on two general tasks (WMT news Zh->En and En->De).

Fast and Accurate Neural Machine Translation with Translation Memory

In this paper, we empirically investigate adversarial attack on NMT from two aspects: languages (the source vs. the target language) and positions (front vs. rear). For autoregressive NMT models that generate target words from left to right, we observe that adversarial attack on the source language is more effective than on the target language, and that attacking front positions of target sentences or positions of source sentences aligned to the front positions of corresponding target sentences is more effective than attacking other positions. We further exploit the attention distribution of the victim model to attack source sentences at positions that have a strong association with front target words. Experiment results demonstrate that our attention-based adversarial attack is more effective than adversarial attacks by sampling positions randomly or according to gradients.

An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter

Although distant supervision automatically generates training data for relation extraction, it also introduces false-positive (FP) and false-negative (FN) training instances to the generated datasets. While both types of errors degrade the final model performance, previous work on distant supervision denoising focuses more on suppressing FP noise and less on resolving the FN problem. We here propose H-FND, a hierarchical false-negative denoising framework for robust distant supervision relation extraction, as an FN denoising solution. H-FND uses a hierarchical policy which first determines whether non-relation (NA) instances should be kept, discarded, or revised during the training process. For those learning instances which are to be revised, the policy further reassigns them appropriate relations, making them better training inputs. Experiments on SemEval-2010 and TACRED were conducted with controlled FN ratios that randomly turn the relations of training and validation instances into negatives to generate FN instances. In this setting, H-FND can revise FN instances correctly and maintains high F1 scores even when 50% of the instances have been turned into negatives. Experiments on NYT10 is further conducted to show that H-FND is applicable in a realistic setting.

H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction

In this paper, we present GEM as a General Evaluation benchmark for Multimodal tasks. Different from existing datasets such as GLUE, SuperGLUE, XGLUE and XTREME that mainly focus on natural language tasks, GEM is a large-scale vision-language benchmark, which consists of for image-language tasks and for video-language tasks. Comparing with existing multimodal datasets such as MSCOCO and Flicker30K for image-language tasks, YouCook2 and MSR-VTT for video-language tasks, GEM is not only the largest vision-language dataset covering image-language tasks and video-language tasks at the same time, but also labeled in multiple languages. We also provide two baseline models for this benchmark. We will release the dataset, code and baseline models, aiming to advance the development of multilingual multimodal research.

{GEM}: A General Evaluation Benchmark for Multimodal Tasks

Syntactic and semantic structure directly reflect relations expressed by the text at hand and are thus very useful for the relation extraction (RE) task. Their symbolic nature allows increased interpretability for end-users and developers, which is particularly appealing in RE. Although they have been somewhat overshadowed recently by the use of end-to-end neural network models and contextualized word embeddings, we show that they may be leveraged as input for neural networks to positive effect. 
We present two methods for integrating broad-coverage semantic structure (specifically, UCCA) into supervised neural RE models, demonstrating benefits over the use of exclusively syntactic integrations. The first method involves reduction of UCCA into a bilexical structure, while the second leverages a novel technique for encoding semantic DAG structures. Our approach is general and can be used for integrating a wide range of graph-based semantic structures.

Paths to Relation Extraction through Semantic Structure

Aspect-based sentiment analysis aims to judge the polarity of the given aspect word in reviews. Most recent methods adopt syntax-based Graph Neural Networks to extract the syntactic information from the dependency graph, thinking that would be beneficial for establishing relations between aspect and opinion words. However, these methods may ignore that some sentences have no remarkable syntactic structure, which causes the opposite judgement in sentiment analysis. In this paper, we figure out this problem by means of optimally fusing syntactic information, semantic information and their combinations simultaneously. Firstly, syntactic graphs and semantic graphs are generated by dependency tree and multi-head self-attention respectively. Then we propose a Dynamic and Multi-channel Graph Convolutional Network (DM-GCN) to learn the correlated information from the generated graphs effectively. Our extensive experiments on SemEval 2014 and Twitter datasets confirm that DM-GCN fuses syntactic, semantic and their combinations optimally and outperforms all state-of-the-art alternatives with a large margin.

Downloads

Next from ACL-IJCNLP 2021

Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort

Similar lecture

Automatic Text Simplification for Social Good: Progress and Challenges

.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 ACL-IJCNLP 2021

Online Learning Meets Machine Translation Evaluation: Finding the Best Systems with the Least Human Effort

Similar lecture

Automatic Text Simplification for Social Good: Progress and Challenges

Downloads