Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization
Dialki: تحديد المعرفة في أنظمة المحادثة من خلال حوار الوثيقة الحوار
343
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن تحديد المعرفة ذات الصلة التي سيتم استخدامها في أنظمة المحادثة التي تستند إلى وثائق طويلة أمر بالغ الأهمية لتوليد الاستجابة الفعال.نقدم نموذج تعريف المعرفة الذي يرفع بنية المستند إلى توفير ترميزات مرور محكوم بحري للحوار ومعرفة تحديد المواقع ذات الصلة بالمحادثة.خسارة مساعدة تلتقط تاريخ اتصالات الوثيقة الحوار.نوضح فعالية نموذجنا على مجموعة بيانات المحادثة المدرجة في المستندات وتوفير التحليلات التي تظهر التعميم على المستندات غير المرئية وسياقات الحوار الطويلة.
Identifying relevant knowledge to be used in conversational systems that are grounded in long documents is critical to effective response generation. We introduce a knowledge identification model that leverages the document structure to provide dialogue-contextualized passage encodings and better locate knowledge relevant to the conversation. An auxiliary loss captures the history of dialogue-document connections. We demonstrate the effectiveness of our model on two document-grounded conversational datasets and provide analyses showing generalization to unseen documents and long dialogue contexts.
References used
https://aclanthology.org/
rate research
Read More
Recent task-oriented dialogue systems learn a model from annotated dialogues, and such dialogues are in turn collected and annotated so that they are consistent with certain domain knowledge. However, in real scenarios, domain knowledge is subject to
frequent changes, and initial training dialogues may soon become obsolete, resulting in a significant decrease in the model performance. In this paper, we investigate the relationship between training dialogues and domain knowledge, and propose Dialogue Domain Adaptation, a methodology aiming at adapting initial training dialogues to changes intervened in the domain knowledge. We focus on slot-value changes (e.g., when new slot values are available to describe domain entities) and define an experimental setting for dialogue domain adaptation. First, we show that current state-of-the-art models for dialogue state tracking are still poorly robust to slot-value changes of the domain knowledge. Then, we compare different domain adaptation strategies, showing that simple techniques are effective to reduce the gap between training dialogues and domain knowledge.
Dialect identification is a task with applicability in a vast array of domains, ranging from automatic speech recognition to opinion mining. This work presents our architectures used for the VarDial 2021 Romanian Dialect Identification subtask. We in
troduced a series of solutions based on Romanian or multilingual Transformers, as well as adversarial training techniques. At the same time, we experimented with a knowledge distillation tool in order to check whether a smaller model can maintain the performance of our best approach. Our best solution managed to obtain a weighted F1-score of 0.7324, allowing us to obtain the 2nd place on the leaderboard.
Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior. We introduce a new human-and-model-in-the-loop framework for evaluati
ng the toxicity of such models, and compare a variety of existing methods in both the cases of non-adversarial and adversarial users that expose their weaknesses. We then go on to propose two novel methods for safe conversational agents, by either training on data from our new human-and-model-in-the-loop framework in a two-stage system, or ''baking-in'' safety to the generative model itself. We find our new techniques are (i) safer than existing models; while (ii) maintaining usability metrics such as engagingness relative to state-of-the-art chatbots. In contrast, we expose serious safety issues in existing standard systems like GPT2, DialoGPT, and BlenderBot.
Most prior work on task-oriented dialogue systems is restricted to supporting domain APIs. However, users may have requests that are out of the scope of these APIs. This work focuses on identifying such user requests. Existing methods for this task m
ainly rely on fine-tuning pre-trained models on large annotated data. We propose a novel method, REDE, based on adaptive representation learning and density estimation. REDE can be applied to zero-shot cases, and quickly learns a high-performing detector with only a few shots by updating less than 3K parameters. We demonstrate REDE's competitive performance on DSTC9 data and our newly collected test set.
Conversational machine reading (CMR) requires machines to communicate with humans through multi-turn interactions between two salient dialogue states of decision making and question generation processes. In open CMR settings, as the more realistic sc
enario, the retrieved background knowledge would be noisy, which results in severe challenges in the information transmission. Existing studies commonly train independent or pipeline systems for the two subtasks. However, those methods are trivial by using hard-label decisions to activate question generation, which eventually hinders the model performance. In this work, we propose an effective gating strategy by smoothing the two dialogue states in only one decoder and bridge decision making and question generation to provide a richer dialogue state reference. Experiments on the OR-ShARC dataset show the effectiveness of our method, which achieves new state-of-the-art results.
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
