اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدInteractive Natural Language-based Person Search
90
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
In this work, we consider the problem of searching people in an unconstrained environment, with natural language descriptions. Specifically, we study how to systematically design an algorithm to effectively acquire descriptions from humans. An algorithm is proposed by adapting models, used for visual and language understanding, to search a person of interest (POI) in a principled way, achieving promising results without the need to re-design another complicated model. We then investigate an iterative question-answering (QA) strategy that enable robots to request additional information about the POIs appearance from the user. To this end, we introduce a greedy algorithm to rank questions in terms of their significance, and equip the algorithm with the capability to dynamically adjust the length of human-robot interaction according to models uncertainty. Our approach is validated not only on benchmark datasets but on a mobile robot, moving in a dynamic and crowded environment.
قيم البحث
اقرأ أيضاً
In this paper, we propose the Interactive Text2Pickup (IT2P) network for human-robot collaboration which enables an effective interaction with a human user despite the ambiguity in users commands. We focus on the task where a robot is expected to pic
k up an object instructed by a human, and to interact with the human when the given instruction is vague. The proposed network understands the command from the human user and estimates the position of the desired object first. To handle the inherent ambiguity in human language commands, a suitable question which can resolve the ambiguity is generated. The users answer to the question is combined with the initial command and given back to the network, resulting in more accurate estimation. The experiment results show that given unambiguous commands, the proposed method can estimate the position of the requested object with an accuracy of 98.49% based on our test dataset. Given ambiguous language commands, we show that the accuracy of the pick up task increases by 1.94 times after incorporating the information obtained from the interaction.
Many search systems work with large amounts of natural language data, e.g., search queries, user profiles, and documents. Building a successful search system requires a thorough understanding of textual data semantics, where deep learning based natur
al language processing techniques (deep NLP) can be of great help. In this paper, we introduce a comprehensive study for applying deep NLP techniques to five representative tasks in search systems: query intent prediction (classification), query tagging (sequential tagging), document ranking (ranking), query auto completion (language modeling), and query suggestion (sequence to sequence). We also introduce BERT pre-training as a sixth task that can be applied to many of the other tasks. Through the model design and experiments of the six tasks, readers can find answers to four important questions: (1). When is deep NLP helpful/not helpful in search systems? (2). How to address latency challenges? (3). How to ensure model robustness? This work builds on existing efforts of LinkedIn search, and is tested at scale on LinkedIns commercial search engines. We believe our experiences can provide useful insights for the industry and research communities.
When parsing unrestricted language, wide-covering grammars often undergenerate. Undergeneration can be tackled either by sentence correction, or by grammar correction. This thesis concentrates upon automatic grammar correction (or machine learning of
grammar) as a solution to the problem of undergeneration. Broadly speaking, grammar correction approaches can be classified as being either {it data-driven}, or {it model-based}. Data-driven learners use data-intensive methods to acquire grammar. They typically use grammar formalisms unsuited to the needs of practical text processing and cannot guarantee that the resulting grammar is adequate for subsequent semantic interpretation. That is, data-driven learners acquire grammars that generate strings that humans would judge to be grammatically ill-formed (they {it overgenerate}) and fail to assign linguistically plausible parses. Model-based learners are knowledge-intensive and are reliant for success upon the completeness of a {it model of grammaticality}. But in practice, the model will be incomplete. Given that in this thesis we deal with undergeneration by learning, we hypothesise that the combined use of data-driven and model-based learning would allow data-driven learning to compensate for model-based learnings incompleteness, whilst model-based learning would compensate for data-driven learnings unsoundness. We describe a system that we have used to test the hypothesis empirically. The system combines data-driven and model-based learning to acquire unification-based grammars that are more suitable for practical text parsing. Using the Spoken English Corpus as data, and by quantitatively measuring undergeneration, overgeneration and parse plausibility, we show that this hypothesis is correct.
This paper presents INGRESS, a robot system that follows human natural language instructions to pick and place everyday objects. The core issue here is the grounding of referring expressions: infer objects and their relationships from input images an
d language expressions. INGRESS allows for unconstrained object categories and unconstrained language expressions. Further, it asks questions to disambiguate referring expressions interactively. To achieve these, we take the approach of grounding by generation and propose a two-stage neural network model for grounding. The first stage uses a neural network to generate visual descriptions of objects, compares them with the input language expression, and identifies a set of candidate objects. The second stage uses another neural network to examine all pairwise relations between the candidates and infers the most likely referred object. The same neural networks are used for both grounding and question generation for disambiguation. Experiments show that INGRESS outperformed a state-of-the-art method on the RefCOCO dataset and in robot experiments with humans.
Recent research efforts enable study for natural language grounded navigation in photo-realistic environments, e.g., following natural language instructions or dialog. However, existing methods tend to overfit training data in seen environments and f
ail to generalize well in previously unseen environments. To close the gap between seen and unseen environments, we aim at learning a generalized navigation model from two novel perspectives: (1) we introduce a multitask navigation model that can be seamlessly trained on both Vision-Language Navigation (VLN) and Navigation from Dialog History (NDH) tasks, which benefits from richer natural language guidance and effectively transfers knowledge across tasks; (2) we propose to learn environment-agnostic representations for the navigation policy that are invariant among the environments seen during training, thus generalizing better on unseen environments. Extensive experiments show that environment-agnostic multitask learning significantly reduces the performance gap between seen and unseen environments, and the navigation agent trained so outperforms baselines on unseen environments by 16% (relative measure on success rate) on VLN and 120% (goal progress) on NDH. Our submission to the CVDN leaderboard establishes a new state-of-the-art for the NDH task on the holdout test set. Code is available at https://github.com/google-research/valan.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
