Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userRAST: Domain-Robust Dialogue Rewriting as Sequence Tagging
RAST: إعادة كتابة الحوار القوي المجال كعلامات تسلسل
278
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تهدف مهمة إعادة كتابة الحوار إلى إعادة بناء أحدث كلام الحوار عن طريق نسخ المحتوى المفقود من سياق الحوار.حتى الآن، تعاني النماذج الحالية لهذه المهمة من مشكلة المتانة، أي أن يؤدي العروض بشكل كبير عند الاختبار على مجموعة مختلفة.نحن نتطلع إلى هذه القضية المتناقصة من خلال اقتراح نموذج يستند إلى تسلسل الرواية بحيث يتم تقليل مساحة البحث بشكل كبير، ومع ذلك، فإن جوهر هذه المهمة لا يزال مغطى جيدا.كمسألة مشتركة من طرازات العلامات في توليد النص، قد تفتقر مخرجات النموذج إلى الطلاقة.لتخفيف هذه المسألة، نفنق إشارة الخسارة من بلو أو GPT-2 بموجب إطار تعزيز.تظهر التجارب تحسينات هائلة في النموذج لدينا عبر الأنظمة الحالية التي من بين الفنون عند النقل إلى مجموعة بيانات أخرى.
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances drop dramatically when testing on a different dataset. We address this robustness issue by proposing a novel sequence-tagging-based model so that the search space is significantly reduced, yet the core of this task is still well covered. As a common issue of most tagging models for text generation, the model's outputs may lack fluency. To alleviate this issue, we inject the loss signal from BLEU or GPT-2 under a REINFORCE framework. Experiments show huge improvements of our model over the current state-of-the-art systems when transferring to another dataset.
References used
https://aclanthology.org/
rate research
Read More
We introduce a new dataset for Question Rewriting in Conversational Context (QReCC), which contains 14K conversations with 80K question-answer pairs. The task in QReCC is to find answers to conversational questions within a collection of 10M web page
s (split into 54M passages). Answers to questions in the same conversation may be distributed across several web pages. QReCC provides annotations that allow us to train and evaluate individual subtasks of question rewriting, passage retrieval and reading comprehension required for the end-to-end conversational question answering (QA) task. We report the effectiveness of a strong baseline approach that combines the state-of-the-art model for question rewriting, and competitive models for open-domain QA. Our results set the first baseline for the QReCC dataset with F1 of 19.10, compared to the human upper bound of 75.45, indicating the difficulty of the setup and a large room for improvement.
This paper describes a system proposed for the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies (EUD). We propose a Graph Rewriting based system for computing Enhanced Universal Dependencies, given the Basic Universal Dependencies (UD).
Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research. The existing literature on open-domain knowledge selection is limited and makes certain brittle assumptions on knowledge
sources to simplify the overall task, such as the existence of a single relevant knowledge sentence per context. In this work, we evaluate the existing state of open-domain conversation knowledge selection, showing where the existing methodologies regarding data and evaluation are flawed. We then improve on them by proposing a new framework for collecting relevant knowledge, and create an augmented dataset based on the Wizard of Wikipedia (WOW) corpus, which we call WOW++. WOW++ averages 8 relevant knowledge sentences per dialogue context, embracing the inherent ambiguity of open-domain dialogue knowledge selection. We then benchmark various knowledge ranking algorithms on this augmented dataset with both intrinsic evaluation and extrinsic measures of response quality, showing that neural rerankers that use WOW++ can outperform rankers trained on standard datasets.
Deriving and modifying graphs from natural language text has become a versatile basis technology for information extraction with applications in many subfields, such as semantic parsing or knowledge graph construction. A recent work used this techniq
ue for modifying scene graphs (He et al. 2020), by first encoding the original graph and then generating the modified one based on this encoding. In this work, we show that we can considerably increase performance on this problem by phrasing it as graph extension instead of graph generation. We propose the first model for the resulting graph extension problem based on autoregressive sequence labelling. On three scene graph modification data sets, this formulation leads to improvements in accuracy over the state-of-the-art between 13 and 24 percentage points. Furthermore, we introduce a novel data set from the biomedical domain which has much larger linguistic variability and more complex graphs than the scene graph modification data sets. For this data set, the state-of-the art fails to generalize, while our model can produce meaningful predictions.
Sequence-to-sequence models have been applied to a wide variety of NLP tasks, but how to properly use them for dialogue state tracking has not been systematically investigated. In this paper, we study this problem from the perspectives of pre-trainin
g objectives as well as the formats of context representations. We demonstrate that the choice of pre-training objective makes a significant difference to the state tracking quality. In particular, we find that masked span prediction is more effective than auto-regressive language modeling. We also explore using Pegasus, a span prediction-based pre-training objective for text summarization, for the state tracking model. We found that pre-training for the seemingly distant summarization task works surprisingly well for dialogue state tracking. In addition, we found that while recurrent state context representation works also reasonably well, the model may have a hard time recovering from earlier mistakes. We conducted experiments on the MultiWOZ 2.1-2.4, WOZ 2.0, and DSTC2 datasets with consistent observations.
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
