Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEnhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval
تعزيز التشفير المزدوج مع السؤال والإجابة على التضامن المتبادلة لاسترجاع الإجابة
394
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
Dual-Encoders هي آلية واعدة لاسترجاع الإجابة في أنظمة الإجابة على الأسئلة (QA). حاليا معظم التشفير المزدوج التقليدية تعلم التمثيل الدلالي للأسئلة والأجوبة فقط من خلال نقاط مطابقة. اقترح الباحثون تقديم ميزات تفاعلات ضمان الجودة في وظيفة التهديف ولكن بتكلفة منخفضة الكفاءة في مرحلة الاستدلال. للحفاظ على الترميز المستقل للأسئلة والأجوبة أثناء مرحلة الاستدلال، يتم تقديم التشفير التلقائي التلقائي بشكل أكبر لإعادة بناء الإجابات (الأسئلة) من Asceddings من السؤال (الإجابة) بمثابة مهمة مساعدة لتعزيز تفاعل QA في مرحلة التدريب في مرحلة التدريب في مرحلة التدريب في مرحلة التدريب في مرحلة التدريب. ومع ذلك، فإن احتياجات جيل النص واسترجاع الإجابة مختلفة، مما يؤدي إلى صلابة في التدريب. في هذا العمل، نقترح إطارا لتعزيز نموذج المشفرين المزدوجين مع الإجابة على السؤال وآلية محاذاة هندسية جديدة (GAM) لمواءمة الهندسة من المدينات من الترميز المزدوج مع ذلك من التشفير عبر التشفير. تظهر النتائج التجريبية الواسعة أن إطارنا يحسن بشكل كبير من طراز الترميز المزدوج وتفوق على الطريقة التي تظهر على مجموعة بيانات استرجاع الإجابة المتعددة.
Dual-Encoders is a promising mechanism for answer retrieval in question answering (QA) systems. Currently most conventional Dual-Encoders learn the semantic representations of questions and answers merely through matching score. Researchers proposed to introduce the QA interaction features in scoring function but at the cost of low efficiency in inference stage. To keep independent encoding of questions and answers during inference stage, variational auto-encoder is further introduced to reconstruct answers (questions) from question (answer) embeddings as an auxiliary task to enhance QA interaction in representation learning in training stage. However, the needs of text generation and answer retrieval are different, which leads to hardness in training. In this work, we propose a framework to enhance the Dual-Encoders model with question answer cross-embeddings and a novel Geometry Alignment Mechanism (GAM) to align the geometry of embeddings from Dual-Encoders with that from Cross-Encoders. Extensive experimental results show that our framework significantly improves Dual-Encoders model and outperforms the state-of-the-art method on multiple answer retrieval datasets.
References used
https://aclanthology.org/
rate research
Read More
In education, quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far,
the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.
Although showing promising values to downstream applications, generating question and answer together is under-explored. In this paper, we introduce a novel task that targets question-answer pair generation from visual images. It requires not only ge
nerating diverse question-answer pairs but also keeping the consistency of them. We study different generation paradigms for this task and propose three models: the pipeline model, the joint model, and the sequential model. We integrate variational inference into these models to achieve diversity and consistency. We also propose region representation scaling and attention alignment to improve the consistency further. We finally devise an evaluator as a quantitative metric for consistency. We validate our approach on two benchmarks, VQA2.0 and Visual-7w, by automatically and manually evaluating diversity and consistency. Experimental results show the effectiveness of our models: they can generate diverse or consistent pairs. Moreover, this task can be used to improve visual question generation and visual question answering.
The evaluation of question answering models compares ground-truth annotations with model predictions. However, as of today, this comparison is mostly lexical-based and therefore misses out on answers that have no lexical overlap but are still semanti
cally similar, thus treating correct answers as false. This underestimation of the true performance of models hinders user acceptance in applications and complicates a fair comparison of different models. Therefore, there is a need for an evaluation metric that is based on semantics instead of pure string similarity. In this short paper, we present SAS, a cross-encoder-based metric for the estimation of semantic answer similarity, and compare it to seven existing metrics. To this end, we create an English and a German three-way annotated evaluation dataset containing pairs of answers along with human judgment of their semantic similarity, which we release along with an implementation of the SAS metric and the experiments. We find that semantic similarity metrics based on recent transformer models correlate much better with human judgment than traditional lexical similarity metrics on our two newly created datasets and one dataset from related work.
Despite excellent performance on tasks such as question answering, Transformer-based architectures remain sensitive to syntactic and contextual ambiguities. Question Paraphrasing (QP) offers a promising solution as a means to augment existing dataset
s. The main challenges of current QP models include lack of training data and difficulty in generating diverse and natural questions. In this paper, we present Conquest, a framework for generating synthetic datasets for contextual question paraphrasing. To this end, Conquest first employs an answer-aware question generation (QG) model to create a question-pair dataset and then uses this data to train a contextualized question paraphrasing model. We extensively evaluate Conquest and show its ability to produce more diverse and fluent question pairs than existing approaches. Our contextual paraphrase model also establishes a strong baseline for end-to-end contextual paraphrasing. Further, We find that context can improve BLEU-1 score on contextual compression and expansion by 4.3 and 11.2 respectively, compared to a non-contextual model.
We study multi-answer retrieval, an under-explored problem that requires retrieving passages to cover multiple distinct answers for a given question. This task requires joint modeling of retrieved passages, as models should not repeatedly retrieve pa
ssages containing the same answer at the cost of missing a different valid answer. Prior work focusing on single-answer retrieval is limited as it cannot reason about the set of passages jointly. In this paper, we introduce JPR, a joint passage retrieval model focusing on reranking. To model the joint probability of the retrieved passages, JPR makes use of an autoregressive reranker that selects a sequence of passages, equipped with novel training and decoding algorithms. Compared to prior approaches, JPR achieves significantly better answer coverage on three multi-answer datasets. When combined with downstream question answering, the improved retrieval enables larger answer generation models since they need to consider fewer passages, establishing a new state-of-the-art.
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
