Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userVisually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History
أسئلة المتابعة الترطفة بصريا: مجموعة بيانات من الأسئلة المكانية التي تتطلب تاريخ الحوار
298
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذه الورقة، نحدد وتقييم منهجية لاستخراج الأسئلة المكانية التي تعتمد على التاريخ من الحوارات البصرية.نقول أن السؤال يعتمد على التاريخ إذا كان يتطلب (أجزاء) تاريخ حواره المراد تفسيره.نقول أن بعض أنواع الأسئلة المرئية تحدد السياق الذي يعتمد عليه سؤال مكاني للمتابعة.نسمي السؤال الذي يقيد السياق: الزناد، ونحن نسمي السؤال المكاني الذي يتطلب الإجابة على سؤال الزناد: Zoomer.نستخرج تلقائيا أزواج الزناد و Zoomer المختلفة بناء على خاصية Visual التي تعتمد الأسئلة عليها (على سبيل المثال، اللون، رقم).نحل تدريجيا يدويا أزواج الزناد و Zoomer المستخرجة تلقائيا للتحقق من أن Zoomers التي تتطلب الزناد.نحن ننفذ بنية أساسية بسيطة بناء على تشفير سوتا متعددة الوسائط.نتائجنا تكشف أن هناك مساحة كبيرة لتحسين الإجابة على الأسئلة التي تعتمد على التاريخ.
In this paper, we define and evaluate a methodology for extracting history-dependent spatial questions from visual dialogues. We say that a question is history-dependent if it requires (parts of) its dialogue history to be interpreted. We argue that some kinds of visual questions define a context upon which a follow-up spatial question relies. We call the question that restricts the context: trigger, and we call the spatial question that requires the trigger question to be answered: zoomer. We automatically extract different trigger and zoomer pairs based on the visual property that the questions rely on (e.g. color, number). We manually annotate the automatically extracted trigger and zoomer pairs to verify which zoomers require their trigger. We implement a simple baseline architecture based on a SOTA multimodal encoder. Our results reveal that there is much room for improvement for answering history-dependent questions.
References used
https://aclanthology.org/
rate research
Read More
Readers of academic research papers often read with the goal of answering specific questions. Question Answering systems that can answer those questions can make consumption of the content much more efficient. However, building such tools requires da
ta that reflect the difficulty of the task arising from complex reasoning about claims made in multiple parts of a paper. In contrast, existing information-seeking question answering datasets usually contain questions about generic factoid-type information. We therefore present Qasper, a dataset of 5049 questions over 1585 Natural Language Processing papers. Each question is written by an NLP practitioner who read only the title and abstract of the corresponding paper, and the question seeks information present in the full text. The questions are then answered by a separate set of NLP practitioners who also provide supporting evidence to answers. We find that existing models that do well on other QA tasks do not perform well on answering these questions, underperforming humans by at least 27 F1 points when answering them from entire papers, motivating further research in document-grounded, information-seeking QA, which our dataset is designed to facilitate.
Predicting the answer to a product-related question is an emerging field of research that recently attracted a lot of attention. Answering subjective and opinion-based questions is most challenging due to the dependency on customer generated content.
Previous works mostly focused on review-aware answer prediction; however, these approaches fail for new or unpopular products, having no (or only a few) reviews at hand. In this work, we propose a novel and complementary approach for predicting the answer for such questions, based on the answers for similar questions asked on similar products. We measure the contextual similarity between products based on the answers they provide for the same question. A mixture-of-expert framework is used to predict the answer by aggregating the answers from contextually similar products. Empirical results demonstrate that our model outperforms strong baselines on some segments of questions, namely those that have roughly ten or more similar resolved questions in the corpus. We additionally publish two large-scale datasets used in this work, one is of similar product question pairs, and the second is of product question-answer pairs.
We investigate ways to compose complex concepts in texts from primitive ones while grounding them in images. We propose Concept and Relation Graph (CRG), which builds on top of constituency analysis and consists of recursively combined concepts with
predicate functions. Meanwhile, we propose a concept composition neural network called Composer to leverage the CRG for visually grounded concept learning. Specifically, we learn the grounding of both primitive and all composed concepts by aligning them to images and show that learning to compose leads to more robust grounding results, measured in text-to-image matching accuracy. Notably, our model can model grounded concepts forming at both the finer-grained sentence level and the coarser-grained intermediate level (or word-level). Composer leads to pronounced improvement in matching accuracy when the evaluation data has significant compound divergence from the training data.
This paper introduces MediaSum, a large-scale media interview dataset consisting of 463.6K transcripts with abstractive summaries. To create this dataset, we collect interview transcripts from NPR and CNN and employ the overview and topic description
s as summaries. Compared with existing public corpora for dialogue summarization, our dataset is an order of magnitude larger and contains complex multi-party conversations from multiple domains. We conduct statistical analysis to demonstrate the unique positional bias exhibited in the transcripts of televised and radioed interviews. We also show that MediaSum can be used in transfer learning to improve a model's performance on other dialogue summarization tasks.
Enabling open-domain dialogue systems to ask clarifying questions when appropriate is an important direction for improving the quality of the system response. Namely, for cases when a user request is not specific enough for a conversation system to p
rovide an answer right away, it is desirable to ask a clarifying question to increase the chances of retrieving a satisfying answer. To address the problem of asking clarifying questions in open-domain dialogues': (1) we collect and release a new dataset focused on open-domain single- and multi-turn conversations, (2) we benchmark several state-of-the-art neural baselines, and (3) we propose a pipeline consisting of offline and online steps for evaluating the quality of clarifying questions in various dialogues. These contributions are suitable as a foundation for further research.
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
