Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated target task. We aim to scrub such undesirable attributes and learn fair re
presentations while maintaining performance on the target task. In this paper, we present an adversarial learning framework Adversarial Scrubber'' (AdS), to debias contextual representations. We perform theoretical analysis to show that our framework converges without leaking demographic information under certain conditions. We extend previous evaluation techniques by evaluating debiasing performance using Minimum Description Length (MDL) probing. Experimental evaluations on 8 datasets show that AdS generates representations with minimal information about demographic attributes while being maximally informative about the target task.
Product reviews and satisfaction surveys seek customer feedback in the form of ranked scales. In these settings, widely used evaluation metrics including F1 and accuracy ignore the rank in the responses (e.g., very likely' is closer to likely' than n
ot at all'). In this paper, we hypothesize that the order of class values is important for evaluating classifiers on ordinal target variables and should not be disregarded. To test this hypothesis, we compared Multi-class Classification (MC) and Ordinal Regression (OR) by applying OR and MC to benchmark tasks involving ordinal target variables using the same underlying model architecture. Experimental results show that while MC outperformed OR for some datasets in accuracy and F1, OR is significantly better than MC for minimizing the error between prediction and target for all benchmarks, as revealed by error-sensitive metrics, e.g. mean-squared error (MSE) and Spearman correlation. Our findings motivate the need to establish consistent, error-sensitive metrics for evaluating benchmarks with ordinal target variables, and we hope that it stimulates interest in exploring alternative losses for ordinal problems.
Recently, the majority of sentiment analysis researchers focus on target-based sentiment analysis because it delivers in-depth analysis with more accurate results as compared to traditional sentiment analysis. In this paper, we propose an interactive
learning approach to tackle a target-based sentiment analysis task for the Arabic language. The proposed IA-LSTM model uses an interactive attention-based mechanism to force the model to focus on different parts (targets) of a sentence. We investigate the ability to use targets, right, and left context, and model them separately to learn their own representations via interactive modeling. We evaluated our model on two different datasets: Arabic hotel review and Arabic book review datasets. The results demonstrate the effectiveness of using this interactive modeling technique for the Arabic target-based task. The model obtained accuracy values of 83.10 compared to SOTA models such as AB-LSTM-PC which obtained 82.60 for the same dataset.
Placeholder translation systems enable the users to specify how a specific phrase is translated in the output sentence. The system is trained to output special placeholder tokens and the user-specified term is injected into the output through the con
text-free replacement of the placeholder token. However and this approach could result in ungrammatical sentences because it is often the case that the specified term needs to be inflected according to the context of the output and which is unknown before the translation. To address this problem and we propose a novel method of placeholder translation that can inflect specified terms according to the grammatical construction of the output sentence. We extend the seq2seq architecture with a character-level decoder that takes the lemma of a user-specified term and the words generated from the word-level decoder to output a correct inflected form of the lemma. We evaluate our approach with a Japanese-to-English translation task in the scientific writing domain and and show our model can incorporate specified terms in a correct form more successfully than other comparable models.
This paper presents the PALI team's winning system for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation. We fine-tune XLM-RoBERTa model to solve the task of word in context disambiguation, i.e., to determine whether
the target word in the two contexts contains the same meaning or not. In implementation, we first specifically design an input tag to emphasize the target word in the contexts. Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not. The new vector is attained by concatenating the embedding of the [CLS] token and the embeddings of the target word in the contexts. In training, we explore several tricks, such as the Ranger optimizer, data augmentation, and adversarial training, to improve the model prediction. Consequently, we attain the first place in all four cross-lingual tasks.
Opinion target extraction and opinion term extraction are two fundamental tasks in Aspect Based Sentiment Analysis (ABSA). Many recent works on ABSA focus on Target-oriented Opinion Words (or Terms) Extraction (TOWE), which aims at extracting the cor
responding opinion words for a given opinion target. TOWE can be further applied to Aspect-Opinion Pair Extraction (AOPE) which aims at extracting aspects (i.e., opinion targets) and opinion terms in pairs. In this paper, we propose Target-Specified sequence labeling with Multi-head Self-Attention (TSMSA) for TOWE, in which any pre-trained language model with multi-head self-attention can be integrated conveniently. As a case study, we also develop a Multi-Task structure named MT-TSMSA for AOPE by combining our TSMSA with an aspect and opinion term extraction module. Experimental results indicate that TSMSA outperforms the benchmark methods on TOWE significantly; meanwhile, the performance of MT-TSMSA is similar or even better than state-of-the-art AOPE baseline models.
A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (
NMT) tasks. However, since the input modalities are different, it is difficult to leverage source language text successfully. In this work, we focus on sequence-level knowledge distillation (SeqKD) from external text-based NMT models. To leverage the full potential of the source language information, we propose backward SeqKD, SeqKD from a target-to-source backward NMT model. To this end, we train a bilingual E2E-ST model to predict paraphrased transcriptions as an auxiliary task with a single decoder. The paraphrases are generated from the translations in bitext via back-translation. We further propose bidirectional SeqKD in which SeqKD from both forward and backward NMT models is combined. Experimental evaluations on both autoregressive and non-autoregressive models show that SeqKD in each direction consistently improves the translation performance, and the effectiveness is complementary regardless of the model capacity.
Non-autoregressive Transformer is a promising text generation model. However, current non-autoregressive models still fall behind their autoregressive counterparts in translation quality. We attribute this accuracy gap to the lack of dependency model
ing among decoder inputs. In this paper, we propose CNAT, which learns implicitly categorical codes as latent variables into the non-autoregressive decoding. The interaction among these categorical codes remedies the missing dependencies and improves the model capacity. Experiment results show that our model achieves comparable or better performance in machine translation tasks than several strong baselines.
Cross-target generalization is a known problem in stance detection (SD), where systems tend to perform poorly when exposed to targets unseen during training. Given that data annotation is expensive and time-consuming, finding ways to leverage abundan
t unlabeled in-domain data can offer great benefits. In this paper, we apply a weakly supervised framework to enhance cross-target generalization through synthetically annotated data. We focus on Twitter SD and show experimentally that integrating synthetic data is helpful for cross-target generalization, leading to significant improvements in performance, with gains in F1 scores ranging from +3.4 to +5.1.
The ultimate goal of this study is to enhance the cultural competence of the Syrian
students at both the school and university phases throughout the teaching of English. The
first part of this study provides what many researchers think about the ro
les of the textbook
and the teacher in strengthening the relationship between the learner and his/her own
culture and/or the other cultures including the target culture. In the second part of this
study, an analysis from a cultural perspective of the Syrian context is provided. This
analysis focuses on the English language textbooks used at the Syrian schools and at
Tishreen university. Then it moves to both the Syrian teachers and leaners. The last part of
this study gives some suggestions that could be helpful in strengthening the cultural
awareness in the Syrian educational system.
