The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries

Carbinell, Jaime; Goldstein, Jade

doi:10.1145/3130348.3130369

Cited by 523 publications

(143 citation statements)

References 3 publications

Supporting

Mentioning

142

Contrasting

Unclassified

Order By: Relevance

“…Also, we plan to evaluate the accuracy in an A/B test to conclude whether a higher system-based and session-based novelty in a session-based offline setting leads to higher user satisfaction. Additionally, we also plan to directly optimize for the beyond-accuracy metrics by incorporating re-ranking techniques (e.g., maximum marginal relevance Carbonell and Goldstein 1998). These evaluations are planned to be carried out in the Talto 15 career platform.…”

Section: Discussionmentioning

confidence: 99%

Using autoencoders for session-based job recommendations

Lacic

Reiter-Haas²,

Kowald

et al. 2020

User Model User-Adap Inter

View full text Add to dashboard Cite

In this work, we address the problem of providing job recommendations in an online session setting, in which we do not have full user histories. We propose a recommendation approach, which uses different autoencoder architectures to encode sessions from the job domain. The inferred latent session representations are then used in a k-nearest neighbor manner to recommend jobs within a session. We evaluate our approach on three datasets, (1) a proprietary dataset we gathered from the Austrian student job portal Studo Jobs, (2) a dataset released by XING after the RecSys 2017 Challenge and (3) anonymized job applications released by CareerBuilder in 2012. Our results show that autoencoders provide relevant job recommendations as well as maintain a high coverage and, at the same time, can outperform state-of-the-art session-based recommendation techniques in terms of system-based and sessionbased novelty.

show abstract

Section: Discussionmentioning

confidence: 99%

Using autoencoders for session-based job recommendations

Lacic

Reiter-Haas²,

Kowald

et al. 2020

User Model User-Adap Inter

View full text Add to dashboard Cite

show abstract

“…The identification of the most salient text units in extractive summarization can be approached as a selection problem, a classification problem, or a ranking problem (Das and Martins 2007). In the selection approach (Carbonell and Goldstein 1998;Nallapati, Zhou, and Ma 2016), units are selected one by one in descending order of relevance, while taking into account the previously selected units. In the classification approach (Kupiec, Pedersen, and Chen 1995;Nallapati, Zhou, and Ma 2016), each unit is classified independently of the other units as either relevant or non-relevant.…”

Section: Methods For Extractive Summarizationmentioning

confidence: 99%

“…Thus, in this paper we address the problem of query-based summarization with short user queries and we evaluate existing methods for that problem. A commonly used method for querybased summarization, especially in the context of web retrieval, is maximal marginal relevance (MMR) (Carbonell and Goldstein 1998). In previous works, MMR was successfully used for extractive summarization of meetings by Murray, Renals, and Carletta (2005), a task that is similar to discussion thread summarization, as meetings also consist of turns from different participants to the discussion.…”

Section: Introductionmentioning

confidence: 99%

Query-based summarization of discussion threads

et al. 2019

View full text Add to dashboard Cite

In this paper, we address query-based summarization of discussion threads. New users can profit from the information shared in the forum, Please check if the inserted city and country names in the affiliations are correct. if they can find back the previously posted information. However, discussion threads on a single topic can easily comprise dozens or hundreds of individual posts. Our aim is to summarize forum threads given real web search queries. We created a data set with search queries from a discussion forum’s search engine log and the discussion threads that were clicked by the user who entered the query. For 120 thread–query combinations, a reference summary was made by five different human raters. We compared two methods for automatic summarization of the threads: a query-independent method based on post features, and Maximum Marginal Relevance (MMR), a method that takes the query into account. We also compared four different word embeddings representations as alternative for standard word vectors in extractive summarization. We find (1) that the agreement between human summarizers does not improve when a query is provided that: (2) the query-independent post features as well as a centroid-based baseline outperform MMR by a large margin; (3) combining the post features with query similarity gives a small improvement over the use of post features alone; and (4) for the word embeddings, a match in domain appears to be more important than corpus size and dimensionality. However, the differences between the models were not reflected by differences in quality of the summaries created with help of these models. We conclude that query-based summarization with web queries is challenging because the queries are short, and a click on a result is not a direct indicator for the relevance of the result.

show abstract

“…•MMR [9] : A typical heuristic method. MMR measures maximal marginal relevancy by balancing relevancy and novelty using weight λ, which is set to optimal value 0.2.…”

Section: Experiments Settingsmentioning

confidence: 99%

“…The formula is based on estimating the marginal relevance, which is defined as a sum of the user-item relevance and the item-items dissimilarity. Based on that criteria, heuristic approaches greedily select items with maximal marginal relevance iteratively [7][8][9]10] . Simple as it is, it's usually hard to guarantee the global optimum of the recommendation list as a result of local greedy item selection [11] .…”

Section: Introductionmentioning

confidence: 99%