Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userContextualized Query Embeddings for Conversational Search
أشرطة استفسار السياق للبحث المحادثة
382
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تصف هذه الورقة نموذجا مدمجا وفعالا لاسترجاع مرور الكمون المنخفض في البحث عن المحادثة بناء على تمثيلات كثيفة علمية. قبل عملنا، يستخدم النهج الواحد من بين الفنون خط أنابيب متعدد المراحل يشتمل على وحدات إعادة صياغة استعلام محادثة واسترجاع المعلومات. على الرغم من فعاليته، غالبا ما يتضمن هذا الخط الأنابيب نماذج عصبية متعددة تتطلب أوقات الاستدلال الطويلة. بالإضافة إلى ذلك، تحسين كل وحدة بشكل مستقل يتجاهل التبعيات بينهم. لمعالجة هذه العيوب، نقترح دمج إعادة صياغة استعلام المحادثة مباشرة في نموذج استرجاع كثيف. للمساعدة في هذا الهدف، نقوم بإنشاء مجموعة بيانات مع ملصقات ذات صلة زائفة للبحث عن المحادثة للتغلب على عدم وجود بيانات تدريب واستكشاف استراتيجيات تدريب مختلفة. نوضح أن نموذجنا يعيد كتابة استعلامات المحادثة بشكل فعال كتمثيلات كثيفة في البحث عن المحادثة والفتح عن نطاق البيانات. أخيرا، بعد مراعاة أن طرازنا يتعلم ضبط نموذج L2 من Arquer Token Ageddings، فإننا نستفيد من هذه الخاصية لاسترجاع الهجين ودعم تحليل الأخطاء.
This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations. Prior to our work, the state-of-the-art approach uses a multi-stage pipeline comprising conversational query reformulation and information retrieval modules. Despite its effectiveness, such a pipeline often includes multiple neural models that require long inference times. In addition, independently optimizing each module ignores dependencies among them. To address these shortcomings, we propose to integrate conversational query reformulation directly into a dense retrieval model. To aid in this goal, we create a dataset with pseudo-relevance labels for conversational search to overcome the lack of training data and to explore different training strategies. We demonstrate that our model effectively rewrites conversational queries as dense representations in conversational search and open-domain question answering datasets. Finally, after observing that our model learns to adjust the L2 norm of query token embeddings, we leverage this property for hybrid retrieval and to support error analysis.
References used
https://aclanthology.org/
rate research
Read More
Query rewrite (QR) is an emerging component in conversational AI systems, reducing user defect. User defect is caused by various reasons, such as errors in the spoken dialogue system, users' slips of the tongue or their abridged language. Many of the
user defects stem from personalized factors, such as user's speech pattern, dialect, or preferences. In this work, we propose a personalized search-based QR framework, which focuses on automatic reduction of user defect. We build a personalized index for each user, which encompasses diverse affinity layers to reflect personal preferences for each user in the conversational AI. Our personalized QR system contains retrieval and ranking layers. Supported by user feedback based learning, training our models does not require hand-annotated data. Experiments on personalized test set showed that our personalized QR system is able to correct systematic and user errors by utilizing phonetic and semantic inputs.
We propose a framework to model an operational conversational negation by applying worldly context (prior knowledge) to logical negation in compositional distributional semantics. Given a word, our framework can create its negation that is similar to
how humans perceive negation. The framework corrects logical negation to weight meanings closer in the entailment hierarchy more than meanings further apart. The proposed framework is flexible to accommodate different choices of logical negations, compositions, and worldly context generation. In particular, we propose and motivate a new logical negation using matrix inverse. We validate the sensibility of our conversational negation framework by performing experiments, leveraging density matrices to encode graded entailment information. We conclude that the combination of subtraction negation and phaser in the basis of the negated word yields the highest Pearson correlation of 0.635 with human ratings.
Growing polarization of the news media has been blamed for fanning disagreement, controversy and even violence. Early identification of polarized topics is thus an urgent matter that can help mitigate conflict. However, accurate measurement of topic-
wise polarization is still an open research challenge. To address this gap, we propose Partisanship-aware Contextualized Topic Embeddings (PaCTE), a method to automatically detect polarized topics from partisan news sources. Specifically, utilizing a language model that has been finetuned on recognizing partisanship of the news articles, we represent the ideology of a news corpus on a topic by corpus-contextualized topic embedding and measure the polarization using cosine distance. We apply our method to a dataset of news articles about the COVID-19 pandemic. Extensive experiments on different news sources and topics demonstrate the efficacy of our method to capture topical polarization, as indicated by its effectiveness of retrieving the most polarized topics.
Conversational semantic role labeling (CSRL) is believed to be a crucial step towards dialogue understanding. However, it remains a major challenge for existing CSRL parser to handle conversational structural information. In this paper, we present a
simple and effective architecture for CSRL which aims to address this problem. Our model is based on a conversational structure aware graph network which explicitly encodes the speaker dependent information. We also propose a multi-task learning method to further improve the model. Experimental results on benchmark datasets show that our model with our proposed training objectives significantly outperforms previous baselines.
The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation (NMT) systems.
However, proposed methods for incorporating pre-trained models are non-trivial and mainly focus on BERT, which lacks a comparison of the impact that other pre-trained models may have on translation performance. In this paper, we demonstrate that simply using the output (contextualized embeddings) of a tailored and suitable bilingual pre-trained language model (dubbed BiBERT) as the input of the NMT encoder achieves state-of-the-art translation performance. Moreover, we also propose a stochastic layer selection approach and a concept of a dual-directional translation model to ensure the sufficient utilization of contextualized embeddings. In the case of without using back translation, our best models achieve BLEU scores of 30.45 for En→De and 38.61 for De→En on the IWSLT'14 dataset, and 31.26 for En→De and 34.94 for De→En on the WMT'14 dataset, which exceeds all published numbers.
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
