Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSelf-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering
تمثل التمثيل المرتبط بالطبيع الذاتي التعبير عن السؤال المستحضر
310
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يتطلب الإجابة السؤال المنطوقة (SQA) فهما غريبا من الوثائق والأسئلة المنطوقة للتنبؤ بالأجواب المثلى. في هذه الورقة، نقترح خطط تدريبية جديدة للسؤال المستحضر الرد على مرحلة تدريب ذاتية الإشراف ومرحلة تعليم التمثيل المتعاقبة. في المرحلة الإشراف ذاتيا، نقترح ثلاث مهام إضافية للإشراف على الذات، بما في ذلك استعادة الكلام وإدراج الكلام، والتمييز على السؤال، وتدريب النموذج المشترك على التقاط الاتساق والتماسك بين وثائق الكلام دون أي بيانات أو شروح إضافية. بعد ذلك اقترحنا تعلم تمثيلات الكلام الثغري في الضوضاء في هدف مرتعيض من خلال اعتماد استراتيجيات تكبير متعددة، بما في ذلك حذف الأمان والإحلال. علاوة على ذلك، نقوم بتصميم اهتمام مؤقت للمحاذاة بمحاذاة أدلة نص الكلام في المساحة المشتركة المستفادة ويفيد مهام SQA. بهذه الطريقة، يمكن أن توجه مخططات التدريب بشكل أكثر فعالية نموذج الجيل للتنبؤ بأجوبة أكثر سليمة. تظهر النتائج التجريبية أن نموذجنا يحصل على نتائج أحدث النتائج على ثلاثة معايير SQA. سيتم توفير الكود الخاص بنا علنا بعد النشر.
Spoken question answering (SQA) requires fine-grained understanding of both spoken documents and questions for the optimal answer prediction. In this paper, we propose novel training schemes for spoken question answering with a self-supervised training stage and a contrastive representation learning stage. In the self-supervised stage, we propose three auxiliary self-supervised tasks, including utterance restoration, utterance insertion, and question discrimination, and jointly train the model to capture consistency and coherence among speech documents without any additional data or annotations. We then propose to learn noise-invariant utterance representations in a contrastive objective by adopting multiple augmentation strategies, including span deletion and span substitution. Besides, we design a Temporal-Alignment attention to semantically align the speech-text clues in the learned common space and benefit the SQA tasks. By this means, the training schemes can more effectively guide the generation model to predict more proper answers. Experimental results show that our model achieves state-of-the-art results on three SQA benchmarks. Our code will be publicly available after publication.
References used
https://aclanthology.org/
rate research
Read More
We propose a method to learn contextualized and generalized sentence representations using contrastive self-supervised learning. In the proposed method, a model is given a text consisting of multiple sentences. One sentence is randomly selected as a
target sentence. The model is trained to maximize the similarity between the representation of the target sentence with its context and that of the masked target sentence with the same context. Simultaneously, the model minimizes the similarity between the latter representation and the representation of a random sentence with the same context. We apply our method to discourse relation analysis in English and Japanese and show that it outperforms strong baseline methods based on BERT, XLNet, and RoBERTa.
Human knowledge is collectively encoded in the roughly 6500 languages spoken around the world, but it is not distributed equally across languages. Hence, for information-seeking question answering (QA) systems to adequately serve speakers of all lang
uages, they need to operate cross-lingually. In this work we investigate the capabilities of multilingually pretrained language models on cross-lingual QA. We find that explicitly aligning the representations across languages with a post-hoc finetuning step generally leads to improved performance. We additionally investigate the effect of data size as well as the language choice in this fine-tuning step, also releasing a dataset for evaluating cross-lingual QA systems.
Large-scale auto-regressive models have achieved great success in dialogue response generation, with the help of Transformer layers. However, these models do not learn a representative latent space of the sentence distribution, making it hard to cont
rol the generation. Recent works have tried on learning sentence representations using Transformer-based framework, but do not model the context-response relationship embedded in the dialogue datasets. In this work, we aim to construct a robust sentence representation learning model, that is specifically designed for dialogue response generation, with Transformer-based encoder-decoder structure. An utterance-level contrastive learning is proposed, encoding predictive information in each context representation for its corresponding response. Extensive experiments are conducted to verify the robustness of the proposed representation learning mechanism. By using both reference-based and reference-free evaluation metrics, we provide detailed analysis on the generated sentences, demonstrating the effectiveness of our proposed model.
Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-constrained, article-summarizing an
swers. We begin by collecting a new dataset of news articles with questions as titles and pairing them with summaries of varying length. This dataset is used to learn a QA pair generation model producing summaries as answers that balance brevity with sufficiency jointly with their corresponding questions. We then reinforce the QA pair generation process with a differentiable reward function to mitigate exposure bias, a common problem in natural language generation. Both automatic metrics and human evaluation demonstrate these QA pairs successfully capture the central gists of the articles and achieve high answer accuracy.
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method with the goal
of learning a better representation of the style and the content. This method is mainly motivated by the recent success of contrastive learning which has demonstrated its power in unsupervised feature extraction tasks. The idea is to design two contrastive losses with respect to the content and the style by considering two problem characteristics during training. One characteristic is that the target sentence shares the same content with the source sentence, and the second characteristic is that the target sentence shares the same style with the exemplar. These two contrastive losses are incorporated into the general encoder-decoder paradigm. Experiments on two datasets, namely QQP-Pos and ParaNMT, demonstrate the effectiveness of our proposed constrastive losses.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
