Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userQuestion answering in Natural Language: the Special Case of Temporal Expressions
الإجابة على اللغة الطبيعية: الحالة الخاصة للتعبيرات الزمنية
419
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من أن الإجابة على الأسئلة العامة قد تم استكشافها جيدا في السنوات الأخيرة، فإن الإجابة السؤال الزمنية هي مهمة لم تتلق أكبر قدر ممكن من التركيز.يهدف عملنا إلى الاستفادة من نهج شعبي المستخدم للاستفادة العامة الإجابة، والإجابة على استخراج، من أجل العثور على إجابات للمسائل الزمنية في الفقرة.لتدريب نموذجنا، نقترح مجموعة بيانات جديدة، مستوحاة من الفريق، وهي سؤال من أحدث سؤال حول كوربوس، خصيصا خصيصا لتوفير معلومات زمنية غنية من خلال تكييف WikiWars، والتي تحتوي على العديد من الوثائق حول أعظم صراعات التاريخ.يوضح تقييمنا أن نموذج مطابق لنموذج التعلم العميق، وغالبا ما يستخدم في الإجابة على السؤال العام، يمكن تكييفه مع السؤال الزمني الرد، إذا قبلنا طرح الأسئلة التي يجب أن تكون إجاباتها موجودة مباشرة في النص.
Although general question answering has been well explored in recent years, temporal question answering is a task which has not received as much focus. Our work aims to leverage a popular approach used for general question answering, answer extraction, in order to find answers to temporal questions within a paragraph. To train our model, we propose a new dataset, inspired by SQuAD, a state-of-the-art question answering corpus, specifically tailored to provide rich temporal information by adapting the corpus WikiWars, which contains several documents on history's greatest conflicts. Our evaluation shows that a pattern matching deep learning model, often used in general question answering, can be adapted to temporal question answering, if we accept to ask questions whose answers must be directly present within a text.
References used
https://aclanthology.org/
rate research
Read More
Multilingual models, such as M-BERT and XLM-R, have gained increasing popularity, due to their zero-shot cross-lingual transfer learning capabilities. However, their generalization ability is still inconsistent for typologically diverse languages and
across different benchmarks. Recently, meta-learning has garnered attention as a promising technique for enhancing transfer learning under low-resource scenarios: particularly for cross-lingual transfer in Natural Language Understanding (NLU). In this work, we propose X-METRA-ADA, a cross-lingual MEta-TRAnsfer learning ADAptation approach for NLU. Our approach adapts MAML, an optimization-based meta-learning approach, to learn to adapt to new languages. We extensively evaluate our framework on two challenging cross-lingual NLU tasks: multilingual task-oriented dialog and typologically diverse question answering. We show that our approach outperforms naive fine-tuning, reaching competitive performance on both tasks for most languages. Our analysis reveals that X-METRA-ADA can leverage limited data for faster adaptation.
Natural Language Inference (NLI) has garnered significant attention in recent years; however, the promise of applying NLI breakthroughs to other downstream NLP tasks has remained unfulfilled. In this work, we use the multiple-choice reading comprehen
sion (MCRC) and checking factual correctness of textual summarization (CFCS) tasks to investigate potential reasons for this. Our findings show that: (1) the relatively shorter length of premises in traditional NLI datasets is the primary challenge prohibiting usage in downstream applications (which do better with longer contexts); (2) this challenge can be addressed by automatically converting resource-rich reading comprehension datasets into longer-premise NLI datasets; and (3) models trained on the converted, longer-premise datasets outperform those trained using short-premise traditional NLI datasets on downstream tasks primarily due to the difference in premise lengths.
Many open-domain question answering problems can be cast as a textual entailment task, where a question and candidate answers are concatenated to form hypotheses. A QA system then determines if the supporting knowledge bases, regarded as potential pr
emises, entail the hypotheses. In this paper, we investigate a neural-symbolic QA approach that integrates natural logic reasoning within deep learning architectures, towards developing effective and yet explainable question answering models. The proposed model gradually bridges a hypothesis and candidate premises following natural logic inference steps to build proof paths. Entailment scores between the acquired intermediate hypotheses and candidate premises are measured to determine if a premise entails the hypothesis. As the natural logic reasoning process forms a tree-like, hierarchical structure, we embed hypotheses and premises in a Hyperbolic space rather than Euclidean space to acquire more precise representations. Empirically, our method outperforms prior work on answering multiple-choice science questions, achieving the best results on two publicly available datasets. The natural logic inference process inherently provides evidence to help explain the prediction process.
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.
Given the more widespread nature of natural language interfaces, it is increasingly important to understand who are accessing those interfaces, and how those interfaces are being used. In this paper, we explore spellchecking in the context of web sea
rch with children as the target audience. In particular, via a literature review we show that, while widely used, popular search tools are ill-designed for children. We then use spellcheckers as a case study to highlight the need for an interdisciplinary approach that brings together natural language processing, education, human-computer interaction to address a known information retrieval problem: query misspelling. We conclude that it is imperative that those for whom the interfaces are designed have a voice in the design process.
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
