Related papers: Co-PACRR: A Context-Aware Neural IR Model for Ad-h…
In product search, users tend to browse results on multiple search result pages (SERPs) (e.g., for queries on clothing and shoes) before deciding which item to purchase. Users' clicks can be considered as implicit feedback which indicates…
Image retrieval from contextual descriptions (IRCD) aims to identify an image within a set of minimally contrastive candidates based on linguistically complex text. Despite the success of VLMs, they still significantly lag behind human…
Conversational agents leveraging AI, particularly deep learning, are emerging in both academic research and real-world applications. However, these applications still face challenges, including disrespecting knowledge and facts, not…
Conversational speech recognition is regarded as a challenging task due to its free-style speaking and long-term contextual dependencies. Prior work has explored the modeling of long-range context through RNNLM rescoring with improved…
Retrieving relevant plots from the book for a query is a critical task, which can improve the reading experience and efficiency of readers. Readers usually only give an abstract and vague description as the query based on their own…
Audio-text retrieval based on natural language descriptions is a challenging task. It involves learning cross-modality alignments between long sequences under inadequate data conditions. In this work, we investigate several audio features…
Contextual reasoning with constraints is crucial for enhancing temporal consistency in cross-frame modeling for visual tracking. However, mainstream tracking algorithms typically associate context by merely stacking historical information…
Pretrained contextualized language models such as BERT and T5 have established a new state-of-the-art for ad-hoc search. However, it is not yet well-understood why these methods are so effective, what makes some variants more effective than…
In the Bag-of-Words (BoW) model based image retrieval task, the precision of visual matching plays a critical role in improving retrieval performance. Conventionally, local cues of a keypoint are employed. However, such strategy does not…
The usage of neural network models puts multiple objectives in conflict with each other: Ideally we would like to create a neural model that is effective, efficient, and interpretable at the same time. However, in most instances we have to…
Retrieval-Augmented Language Modeling (RALM) methods, which condition a language model (LM) on relevant documents from a grounding corpus during generation, were shown to significantly improve language modeling performance. In addition,…
According to the Probability Ranking Principle (PRP), ranking documents in decreasing order of their probability of relevance leads to an optimal document ranking for ad-hoc retrieval. The PRP holds when two conditions are met: [C1] the…
Context-Aware Emotion Recognition (CAER) is a crucial and challenging task that aims to perceive the emotional states of the target person with contextual information. Recent approaches invariably focus on designing sophisticated…
Position embeddings, encoding the positional relationships among tokens in text sequences, make great contributions to modeling local context features in Transformer-based pre-trained language models. However, in Extractive Question…
In-context learning (ICL) is the ability of a model to learn a new task by observing a few exemplars in its context. While prevalent in NLP, this capability has recently also been observed in Reinforcement Learning (RL) settings. Prior…
Extracting valuable facts or informative summaries from multi-dimensional tables, i.e. insight mining, is an important task in data analysis and business intelligence. However, ranking the importance of insights remains a challenging and…
A peculiarity of conversational search systems is that they involve mixed-initiatives such as system-generated query clarifying questions. Evaluating those systems at a large scale on the end task of IR is very challenging, requiring…
Neural ranking models are traditionally trained on a series of random batches, sampled uniformly from the entire training set. Curriculum learning has recently been shown to improve neural models' effectiveness by sampling batches…
Retrieving partially relevant segments from untrimmed videos remains difficult due to two persistent challenges: the mismatch in information density between text and video segments, and limited attention mechanisms that overlook semantic…
While image captioning through machines requires structured learning and basis for interpretation, improvement requires multiple context understanding and processing in a meaningful way. This research will provide a novel concept for…